© 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. 24-TRANSCODER-HP
    7. 150310
    Prev
    Next
    INDEX
    Explanations

    Cap

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ighter
    -0.26
    ardy
    -0.25
    echa
    -0.25
    illian
    -0.24
    prev
    -0.23
     adultes
    -0.23
    ä¸Ĭ次
    -0.23
    æĥ³äºĨ
    -0.23
     behalf
    -0.23
    actable
    -0.23
    POSITIVE LOGITS
    less
    0.32
    ary
    0.31
    nets
    0.29
    ri
    0.28
    ses
    0.26
    uet
    0.26
    ul
    0.26
    ulative
    0.25
    es
    0.25
    en
    0.25
    Activations Density 1.439%

    No Known Activations