© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 151245
    Prev
    Next
    INDEX
    Explanations

    numerical analysis/math formulas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     meshes
    -0.28
    满
    -0.27
    æ´¹
    -0.26
    mach
    -0.25
     reflex
    -0.25
     Mess
    -0.24
    说èĩªå·±
    -0.24
    äºĴåĬ¨
    -0.24
    ëģĦ
    -0.24
     incidence
    -0.24
    POSITIVE LOGITS
     Monetary
    0.29
    STER
    0.29
    LAG
    0.28
    aign
    0.27
    ster
    0.27
    _WS
    0.26
    .Fire
    0.26
    åĨľä¸ļåĨľæĿij
    0.25
    GROUND
    0.25
    ooter
    0.25
    Activations Density 0.139%

    No Known Activations