Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 131071
    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arguing
    -0.08
     linha
    -0.07
     alunos
    -0.07
    _vote
    -0.07
     ביקש
    -0.07
     pals
    -0.07
    大脑
    -0.07
     Based
    -0.07
    -girl
    -0.06
     spontaneous
    -0.06
    POSITIVE LOGITS
    愃
    0.07
    (th
    0.07
    QString
    0.07
    irmware
    0.07
    🅾
    0.07
     Wein
    0.07
     każdej
    0.06
     fx
    0.06
     FAG
    0.06
    INTERN
    0.06
    Activations Density 0.013%

    No Known Activations