© 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. 7-RESID-POST-AA
    11. 81767
    Prev
    Next
    INDEX
    Explanations

    Pra

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hardest
    -0.08
     setError
    -0.08
    opened
    -0.07
    ركز
    -0.07
     العربية
    -0.07
    𝐭
    -0.07
    jec
    -0.06
     signup
    -0.06
     duration
    -0.06
     Military
    -0.06
    POSITIVE LOGITS
     Klopp
    0.08
     tract
    0.07
    .scss
    0.07
    区管委会
    0.07
    雒
    0.06
    routine
    0.06
    습니까
    0.06
    יפול
    0.06
    irms
    0.06
    =*
    0.06
    Activations Density 0.001%

    No Known Activations