© 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. 8106
    Prev
    Next
    INDEX
    Explanations

    scenes

    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
    sphere
    -0.29
    perms
    -0.29
    YL
    -0.28
    éĻ¶
    -0.28
    rende
    -0.27
     pretended
    -0.26
    治好
    -0.25
    tensor
    -0.25
    æīİ
    -0.25
    åħ¶æ¬¡æĺ¯
    -0.25
    POSITIVE LOGITS
     engineering
    0.28
    éĤ£è¾¹
    0.26
     near
    0.26
    é¢Ŀ度
    0.26
     grid
    0.26
     elsewhere
    0.26
     chez
    0.25
     upkeep
    0.25
     bedroom
    0.24
    leep
    0.24
    Activations Density 0.002%

    No Known Activations