© 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. 9412
    Prev
    Next
    INDEX
    Explanations

    Computer code and low values

    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
     penc
    -0.28
    apor
    -0.28
    å¾ĹåĪĨ
    -0.28
    posal
    -0.28
     Drawable
    -0.27
    计
    -0.26
    å¾Ĺ好
    -0.26
     Cleaning
    -0.26
    è¯ĦåĪĨ
    -0.26
    .sav
    -0.26
    POSITIVE LOGITS
    秣
    0.28
     chain
    0.27
    bst
    0.26
    èĪ¹
    0.26
    chain
    0.26
     opinions
    0.25
     shut
    0.25
     mag
    0.25
    æĥħæĬ¥
    0.25
    Ĭ¶æĢģ
    0.24
    Activations Density 0.004%

    No Known Activations