© 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. 29755
    Prev
    Next
    INDEX
    Explanations

    video game elements

    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
     cub
    -0.29
    éĢĭ
    -0.28
     Squad
    -0.27
    efficient
    -0.26
    åħļçļĦé¢Ĩ导
    -0.24
    æ¿ij
    -0.24
    ẳ
    -0.24
    ä¸Ĭå¹´
    -0.24
    -blind
    -0.23
     Schn
    -0.23
    POSITIVE LOGITS
    igram
    0.29
    涯
    0.26
    ront
    0.26
    iment
    0.25
    rit
    0.25
    igue
    0.25
    arium
    0.25
    第ä¸Ģ书记
    0.24
    cré
    0.24
    ernet
    0.24
    Activations Density 0.634%

    No Known Activations