© 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. 23-TRANSCODER-HP
    7. 23721
    Prev
    Next
    INDEX
    Explanations

    anyone

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inev
    -0.29
    æķ´è½¦
    -0.26
     defect
    -0.25
     verg
    -0.25
    缼
    -0.25
    临æŶ
    -0.25
     bolt
    -0.25
    awei
    -0.24
    roots
    -0.24
    åĤ»
    -0.24
    POSITIVE LOGITS
     Ment
    0.30
     Authors
    0.26
    (copy
    0.26
     Medal
    0.25
    otch
    0.25
    hausen
    0.24
    :http
    0.24
     Yield
    0.24
    .Match
    0.24
     Princip
    0.24
    Activations Density 0.137%

    No Known Activations