© 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. 29686
    Prev
    Next
    INDEX
    Explanations

    code imports

    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
    omencl
    -0.26
    è§
    -0.25
    uct
    -0.25
    ...]
    -0.24
    ongan
    -0.24
    å±±ä¸Ĭ
    -0.24
    æĺİçŁ¥
    -0.24
    бÑĭÑĤ
    -0.24
    第ä¸īåŃ£åº¦
    -0.24
    tol
    -0.23
    POSITIVE LOGITS
     fal
    0.27
    ~
    0.26
     Ent
    0.26
    éc
    0.26
    enton
    0.25
    -Sep
    0.25
     curl
    0.25
    Ent
    0.25
     Estates
    0.25
     cours
    0.25
    Activations Density 1.342%

    No Known Activations