© 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. 41874
    Prev
    Next
    INDEX
    Explanations

    3

    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
    æıIJä¾Ľ
    -0.68
     provide
    -0.59
     Provide
    -0.59
    æıIJä¾ĽäºĨ
    -0.57
     provides
    -0.56
    provide
    -0.55
    Provide
    -0.55
     offers
    -0.53
     offer
    -0.53
     Offer
    -0.52
    POSITIVE LOGITS
    uze
    0.29
    gren
    0.26
     mob
    0.25
     Mob
    0.25
     Venez
    0.24
     defended
    0.24
    avian
    0.24
    çī¡
    0.24
     touring
    0.23
    ãĥĽãĥ¼ãĥ«
    0.23
    Activations Density 0.005%

    No Known Activations