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. 2869
    Prev
    Next
    INDEX
    Explanations

    exact

    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
    效果图
    -0.08
     sân
    -0.07
     여
    -0.07
    操场
    -0.07
     BitSet
    -0.07
    lickr
    -0.07
     coco
    -0.07
    月底
    -0.07
    Ὀ
    -0.06
    면서
    -0.06
    POSITIVE LOGITS
     simply
    0.07
    ENT
    0.07
    店主
    0.07
     managerial
    0.07
     Mart
    0.07
    ясн
    0.07
     государ
    0.07
    criptive
    0.07
    GUID
    0.07
     guessing
    0.07
    Activations Density 0.012%

    No Known Activations