© 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. 30052
    Prev
    Next
    INDEX
    Explanations

    animals

    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
    ater
    -0.30
    quin
    -0.27
     ours
    -0.27
    iline
    -0.27
    æĸ
    -0.25
    itionally
    -0.25
    asl
    -0.25
    æ¸ħæī«
    -0.25
    æĮ£éĴ±
    -0.25
    éĵ¸
    -0.25
    POSITIVE LOGITS
     blasted
    0.28
    è¶ħé¢Ŀ
    0.27
    ritt
    0.26
     automát
    0.25
     Rays
    0.25
     ei
    0.25
     li
    0.25
    Instantiate
    0.25
     CHAR
    0.25
     rusty
    0.25
    Activations Density 0.987%

    No Known Activations