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. 71271
    Prev
    Next
    INDEX
    Explanations

    code

    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
    .code
    -0.08
     EH
    -0.07
    电
    -0.07
    茹
    -0.07
    𝒜
    -0.07
    temp
    -0.07
    .MustCompile
    -0.07
    hoe
    -0.07
    歌舞
    -0.07
    _DIST
    -0.06
    POSITIVE LOGITS
    Formats
    0.08
    ROID
    0.07
    plätze
    0.07
     Meadow
    0.07
    —or
    0.06
    /dom
    0.06
    �权
    0.06
     المباشر
    0.06
    !',↵
    0.06
    ifle
    0.06
    Activations Density 0.001%

    No Known Activations