© 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 EvalsExportsAPI 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. 78671
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    变幻
    -0.08
    粮油
    -0.07
    ʿ
    -0.07
    ৺
    -0.07
    主要内容
    -0.07
    וידאו
    -0.07
     inputStream
    -0.07
    Ϲ
    -0.07
     slain
    -0.07
    .WHITE
    -0.07
    POSITIVE LOGITS
    éta
    0.07
    زم
    0.07
    战略
    0.07
    应用场景
    0.07
     Typ
    0.07
    'n
    0.07
    -fix
    0.07
     Barth
    0.07
    swap
    0.06
     harvesting
    0.06
    Activations Density 0.022%

    No Known Activations