© 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. 41473
    Prev
    Next
    INDEX
    Explanations

    gaz

    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
    æĿ¯
    -0.33
    ainen
    -0.26
    appen
    -0.25
    icum
    -0.25
     cup
    -0.25
    isel
    -0.25
     LX
    -0.25
    isex
    -0.25
    &type
    -0.25
    ç«Ļèµ·æĿ¥
    -0.24
    POSITIVE LOGITS
    çIJĨæĢ§
    0.29
    ãĥ©ãĥ³ãĤ¹
    0.27
    çĸı
    0.25
    acter
    0.24
    hab
    0.24
     Cursors
    0.24
    SIDE
    0.24
    anchise
    0.24
    å½ĵäºĭ
    0.24
    .readyState
    0.24
    Activations Density 0.001%

    No Known Activations