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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 31206
    Prev
    Next
    INDEX
    Explanations

    uso

    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
    גישה
    -0.08
    ighting
    -0.08
    张先生
    -0.07
    お話
    -0.07
     mistress
    -0.07
     lash
    -0.07
    hat
    -0.07
    ければ
    -0.06
    מן
    -0.06
    ipv
    -0.06
    POSITIVE LOGITS
    _CLASSES
    0.08
     Inn
    0.07
    .fs
    0.07
    同样
    0.07
     ngạc
    0.07
     klub
    0.07
    楼房
    0.07
    -danger
    0.07
    @(
    0.07
     новых
    0.07
    Activations Density 0.914%

    No Known Activations