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. 88390
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     rowNum
    -0.07
    _exam
    -0.07
    xaa
    -0.07
    .parseLong
    -0.07
     beat
    -0.07
    _MIDDLE
    -0.07
     Zoe
    -0.07
    arez
    -0.06
    征集
    -0.06
    /tag
    -0.06
    POSITIVE LOGITS
    mart
    0.07
    や
    0.07
    כלול
    0.07
    fish
    0.07
    _terms
    0.06
     toughness
    0.06
    八
    0.06
    бри
    0.06
     Kl
    0.06
    舟
    0.06
    Activations Density 0.078%

    No Known Activations