© 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. 29155
    Prev
    Next
    INDEX
    Explanations

    osis

    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
    ughters
    -0.29
    éĩİå¤ĸ
    -0.28
    earch
    -0.26
     bulky
    -0.26
    .bind
    -0.25
    ear
    -0.25
    hits
    -0.25
    ôle
    -0.24
    lood
    -0.23
    //}}
    -0.23
    POSITIVE LOGITS
     reel
    0.30
    [in
    0.28
    esa
    0.27
    åĢį
    0.27
     reels
    0.27
    饿
    0.26
    åIJ«
    0.25
    bel
    0.25
     ksi
    0.24
     Norman
    0.24
    Activations Density 2.220%

    No Known Activations