© 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. 29776
    Prev
    Next
    INDEX
    Explanations

    old technology/coding practices

    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
    ä¸ĩæĪ·
    -0.26
    æĽĻ
    -0.25
    汶å·Ŀ
    -0.25
    referrer
    -0.25
    åĽĽå¤§
    -0.24
    å·¡
    -0.24
     progen
    -0.24
     torrents
    -0.24
    agens
    -0.24
    岩
    -0.23
    POSITIVE LOGITS
    atics
    0.31
    <![
    0.29
    oy
    0.27
    ãģŀ
    0.27
    禽
    0.27
    好似
    0.27
     effective
    0.26
    oir
    0.25
     Kund
    0.25
    ised
    0.24
    Activations Density 0.087%

    No Known Activations