© 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. 9-TRANSCODER-HP
    7. 30347
    Prev
    Next
    INDEX
    Explanations

    Code/identifiers and food fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    dba
    -0.29
    æĻ
    -0.29
     Bun
    -0.26
    lie
    -0.26
    bond
    -0.25
    (ST
    -0.25
     unprotected
    -0.25
    lä
    -0.24
    ama
    -0.24
    ty
    -0.24
    POSITIVE LOGITS
    APPLICATION
    0.29
    ä¾ĽåĽ¾
    0.28
    åģ¶
    0.28
     voluntary
    0.26
     application
    0.25
     Application
    0.25
     flavour
    0.25
    åºĶçĶ¨åľºæĻ¯
    0.25
    <Application
    0.25
     quickest
    0.25
    Activations Density 0.467%

    No Known Activations