© 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. 8167
    Prev
    Next
    INDEX
    Explanations

    Computer code and medical texts

    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
    itude
    -0.27
    edis
    -0.26
    èĢIJ
    -0.26
    vens
    -0.25
    主åĬ¨
    -0.25
    á»įng
    -0.24
    utive
    -0.24
    æł¸åĩĨ
    -0.24
    ROWN
    -0.24
     Pager
    -0.23
    POSITIVE LOGITS
    èĢĮå·²
    0.30
    atar
    0.27
     meet
    0.26
    æĿł
    0.26
    设å¤ĩ
    0.25
    oplan
    0.25
    å¿ĥçģµ
    0.25
    adoras
    0.24
    \param
    0.24
    éĤ£ç§į
    0.24
    Activations Density 0.000%

    No Known Activations