© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 29651
    Prev
    Next
    INDEX
    Explanations

    technical content

    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
    äºļ
    -0.31
    âĢ¦
    -0.29
    游
    -0.27
    箫
    -0.26
    elog
    -0.25
    joy
    -0.25
    纪念é¦Ĩ
    -0.25
    ámara
    -0.25
    主
    -0.24
    âĢ¦âĢ¦
    -0.24
    POSITIVE LOGITS
    çļĦæľĢåIJİä¸Ģ
    0.27
    åľ¨åŃ¦æł¡
    0.26
    åİ¢
    0.26
    ousse
    0.26
    bih
    0.25
    åľ¨ä¸Ĭæµ·
    0.25
    pellier
    0.24
     loadChildren
    0.24
    à¹Ĥà¸Ĺร
    0.24
     patri
    0.24
    Activations Density 2.283%

    No Known Activations