© 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. 30173
    Prev
    Next
    INDEX
    Explanations

    academic/scientific texts

    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
    Not in Any Lists

    No Comments

    Negative Logits
     vibrator
    -0.26
     porch
    -0.26
    èĮĥ
    -0.26
     Pot
    -0.25
    -format
    -0.25
     inbox
    -0.24
    å¢Ģ
    -0.24
    ç»ıéªĮåĴĮ
    -0.24
    ترا
    -0.24
    por
    -0.23
    POSITIVE LOGITS
    emme
    0.32
    æĺ¥åŃ£
    0.28
    ä¸įæľį
    0.27
    otyp
    0.26
    èĤŁ
    0.25
    <pre
    0.25
    佩
    0.25
    åħĪè¿Ľåįķä½į
    0.24
    åĽĽçº§
    0.24
    æĻĵ
    0.24
    Activations Density 2.815%

    No Known Activations