© 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. 57298
    Prev
    Next
    INDEX
    Explanations

    names and foreign words

    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
    rate
    -0.29
    :o
    -0.28
    qe
    -0.26
    å·¥èµĦ
    -0.25
    bor
    -0.25
    åĪ©æģ¯
    -0.25
     rate
    -0.25
    æĺ¯éŁ©åĽ½
    -0.25
    æĢ¨
    -0.25
     Taste
    -0.24
    POSITIVE LOGITS
    -Clause
    0.33
    èĤ¢
    0.28
    edly
    0.28
    ely
    0.25
    åħ¬æ°ij
    0.25
    ä¸įå¾Ĺ转载
    0.24
     simulation
    0.24
     lied
    0.24
    eth
    0.23
     ********************************************************
    0.23
    Activations Density 0.026%

    No Known Activations