© 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. 32-TRANSCODER-HP
    7. 43369
    Prev
    Next
    INDEX
    Explanations

    bacterial

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     path
    -0.30
    kul
    -0.28
    leck
    -0.28
    CR
    -0.26
    fit
    -0.26
    第ä¸ĢæĿ¡
    -0.25
     Path
    -0.25
     UCS
    -0.25
    Fe
    -0.25
     Fe
    -0.25
    POSITIVE LOGITS
    archical
    0.28
     Profile
    0.26
    éĵº
    0.26
    profiles
    0.26
    oxy
    0.24
    amina
    0.24
    yll
    0.24
    æĤĴ
    0.24
    _profiles
    0.24
    PROFILE
    0.24
    Activations Density 0.002%

    No Known Activations