© 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. 9316
    Prev
    Next
    INDEX
    Explanations

    =

    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
    è¿ĻéĩĮæľī
    -0.40
     here
    -0.36
    è¿ĻéĩĮ
    -0.32
    è¿ĺæľī
    -0.32
    _here
    -0.29
     HERE
    -0.29
     THERE
    -0.29
    еÑĢе
    -0.29
    rics
    -0.27
    here
    -0.27
    POSITIVE LOGITS
    dispatch
    0.29
     regime
    0.28
    éĢļå¾Ģ
    0.27
     contributions
    0.26
    _dispatch
    0.26
     regimes
    0.25
    Sharper
    0.25
    人寿
    0.25
     Contributions
    0.25
    usal
    0.24
    Activations Density 0.022%

    No Known Activations