© 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. 30012
    Prev
    Next
    INDEX
    Explanations

    stages or phases

    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
    ustum
    -0.27
    tá
    -0.26
     <",
    -0.26
    IENT
    -0.26
    æĬķ
    -0.26
    tical
    -0.25
     Pompeo
    -0.25
    @stop
    -0.24
    ëŀĮ
    -0.24
    olta
    -0.24
    POSITIVE LOGITS
    Haz
    0.29
    è¾ĥéķ¿
    0.28
    ØŃÙĪ
    0.26
    èĪ¬
    0.25
    ä¸ĢèĪ¬äºº
    0.25
    好人
    0.25
    rox
    0.24
    人
    0.24
    ill
    0.24
    ä¸ĢèĪ¬çļĦ
    0.24
    Activations Density 2.699%

    No Known Activations