© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 8419
    Prev
    Next
    INDEX
    Explanations

    nonprofit organizations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸įåĬ¨
    -0.31
    egen
    -0.30
    memberof
    -0.26
    满äºĨ
    -0.26
     Stern
    -0.25
    itime
    -0.25
    ä¼ļ被
    -0.25
     province
    -0.24
    ä¸įéĶĪ
    -0.24
     eigen
    -0.24
    POSITIVE LOGITS
    æĬ¼
    0.33
    å±Ĥå±Ĥ
    0.30
     {:
    0.28
    acco
    0.27
    åľ¨ç½ij绾
    0.26
    è¸ı
    0.25
    odal
    0.25
    é½Ĭ
    0.25
    des
    0.24
     dereg
    0.24
    Activations Density 0.004%

    No Known Activations