© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 23953
    Prev
    Next
    INDEX
    Explanations

    Numbers, code, Chinese text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recal
    -0.28
    refer
    -0.26
    developers
    -0.26
    计ç®ĹåĻ¨
    -0.26
    don
    -0.25
     Refer
    -0.24
     startPos
    -0.24
    _SOUND
    -0.24
    è·µ
    -0.24
    loader
    -0.24
    POSITIVE LOGITS
     Dag
    0.32
    inges
    0.30
    igrations
    0.30
     pill
    0.28
    !--
    0.26
    snapshot
    0.26
    ings
    0.25
    Ĥ¹
    0.25
     Ach
    0.25
     plank
    0.25
    Activations Density 0.001%

    No Known Activations