© 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. 29975
    Prev
    Next
    INDEX
    Explanations

    hydrogen

    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
    åıĹçĽĬ
    -0.28
     concerns
    -0.26
    ãģ®ãĤĤ
    -0.26
    ĪæĿĥ
    -0.26
     Bas
    -0.26
    ç´Ģ
    -0.26
     bas
    -0.26
    XYZ
    -0.26
     Parse
    -0.25
    dec
    -0.25
    POSITIVE LOGITS
    çĻ½èıľ
    0.26
    perature
    0.26
    èĻ¢
    0.26
    obbies
    0.25
    udoku
    0.25
    datable
    0.25
    slideDown
    0.25
    ombo
    0.24
    _CRITICAL
    0.24
     timetable
    0.24
    Activations Density 0.086%

    No Known Activations