© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 60748
    Prev
    Next
    INDEX
    Explanations

    terms and phrases about cryptography, encryption, and secure-communication technology.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    способ
    -0.07
     Lafayette
    -0.06
    三十年
    -0.06
    すること
    -0.06
    愔
    -0.06
    らない
    -0.06
     reins
    -0.06
     hann
    -0.06
    抗击疫情
    -0.06
    -role
    -0.06
    POSITIVE LOGITS
    栗
    0.07
     Teams
    0.07
     GetUser
    0.07
     Destiny
    0.07
    #\
    0.07
     slashed
    0.06
     etiqu
    0.06
    Bl
    0.06
    뺐
    0.06
     numRows
    0.06
    Activations Density 0.052%

    No Known Activations