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. 35972
    Prev
    Next
    INDEX
    Explanations

    say "births"

    np_max-act-logits · gemini-2.0-flash
    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
    乡村振兴
    -0.08
     Brig
    -0.08
     fian
    -0.07
    ión
    -0.07
     À
    -0.07
    ocê
    -0.07
    ,copy
    -0.07
    zzarella
    -0.06
    修剪
    -0.06
    משפ
    -0.06
    POSITIVE LOGITS
    下调
    0.07
    ][
    0.06
    ꡕ
    0.06
    𥕢
    0.06
    ietf
    0.06
    ящих
    0.06
    Grant
    0.06
     sau
    0.06
    _PRESENT
    0.06
     Lazar
    0.06
    Activations Density 0.002%

    No Known Activations