© 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. 32-TRANSCODER-HP
    7. 43066
    Prev
    Next
    INDEX
    Explanations

    Sentence/topic beginnings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Pin
    -0.30
    å¾Ĺ天
    -0.26
    æĸ°èģŀ
    -0.26
    .executeUpdate
    -0.26
     commenter
    -0.25
    饵
    -0.25
     Comment
    -0.25
    sein
    -0.25
     entered
    -0.25
     thro
    -0.25
    POSITIVE LOGITS
     mileage
    0.28
    å²ģ以ä¸ĭ
    0.28
    idel
    0.28
    \Context
    0.26
    lical
    0.26
     Speedway
    0.25
    碾
    0.25
    aged
    0.25
    unu
    0.25
    _Description
    0.24
    Activations Density 0.000%

    No Known Activations