© 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. 29817
    Prev
    Next
    INDEX
    Explanations

    up

    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
    æĺ¨
    -0.27
    综
    -0.27
    celain
    -0.27
    绵
    -0.26
    解åĨ³æĸ¹æ¡Ī
    -0.25
    æ±¾
    -0.25
    æĺĶ
    -0.25
    erner
    -0.25
     .$
    -0.25
     Blu
    -0.25
    POSITIVE LOGITS
    id
    0.28
    CMS
    0.27
     boundary
    0.26
    ä¸Ģåij³
    0.26
    åħ¥åĽŃ
    0.25
    idas
    0.25
     bounding
    0.24
    åIJİéĿ¢çļĦ
    0.24
     ad
    0.24
    åģļæ³ķ
    0.24
    Activations Density 1.755%

    No Known Activations