© 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. 29868
    Prev
    Next
    INDEX
    Explanations

    antibody

    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
     Nam
    -0.28
    avor
    -0.28
    ewn
    -0.27
    ewe
    -0.26
    éĻ¤
    -0.26
    éĻ¤åİ»
    -0.26
     sanitize
    -0.25
    boost
    -0.25
     Ty
    -0.25
    rozen
    -0.24
    POSITIVE LOGITS
    åĴĮæĬĢæľ¯
    0.33
    模
    0.30
     Gund
    0.29
    åĪijäºĭæ¡Ī件
    0.28
     Hannah
    0.28
     bod
    0.27
    artic
    0.27
    åĴĮ个人
    0.26
    Prem
    0.25
    åĭĥ
    0.25
    Activations Density 0.149%

    No Known Activations