© 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. 9433
    Prev
    Next
    INDEX
    Explanations

    Formal writing, documentation, research papers

    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
    人æķ°
    -0.29
    人æŃ»äº¡
    -0.27
    人å¿ĥ
    -0.27
    ingly
    -0.25
    åĺīåħ´
    -0.25
    人
    -0.25
    airo
    -0.25
    æ¾ī
    -0.24
    angu
    -0.24
    engl
    -0.24
    POSITIVE LOGITS
    spy
    0.28
    æĭĸ
    0.26
    ç§ĭåĨ¬
    0.26
    该æ¡Ī
    0.26
    ä¿¡
    0.26
    tie
    0.25
    á»Ħ
    0.25
     penet
    0.25
     Seah
    0.25
     Bik
    0.25
    Activations Density 0.000%

    No Known Activations