© 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. 8387
    Prev
    Next
    INDEX
    Explanations

    as

    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
    Marshal
    -0.27
    cribes
    -0.25
    _LINES
    -0.25
    åIJĴ
    -0.25
    hazi
    -0.24
    ä¸Ģæīĭ
    -0.24
    ä¸Ģ头
    -0.24
    è¯ī
    -0.24
    çī¹æ®ĬæĥħåĨµ
    -0.24
    icz
    -0.24
    POSITIVE LOGITS
     еÑģÑĤÑĮ
    0.33
    æĺ¯
    0.30
     existence
    0.30
     exist
    0.28
     isr
    0.28
     is
    0.27
    ãģ«ãģ¯
    0.27
    ìŀĩ
    0.27
    IS
    0.27
    æĺ¯éŁ©åĽ½
    0.26
    Activations Density 0.013%

    No Known Activations