© 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. 33-TRANSCODER-HP
    7. 53532
    Prev
    Next
    INDEX
    Explanations

    Food and cooking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rollers
    -0.29
     sliding
    -0.24
     çĻ»
    -0.24
    Slice
    -0.24
    move
    -0.24
    оÑħÑĢан
    -0.24
    store
    -0.24
    roller
    -0.24
    .shtml
    -0.24
    æµ®åĬ¨
    -0.23
    POSITIVE LOGITS
    èĤĺ
    0.28
    ãģıãĤĮ
    0.26
     republic
    0.25
    lor
    0.25
     Bez
    0.25
    ods
    0.25
    .Be
    0.24
    зав
    0.24
    -be
    0.24
    odic
    0.23
    Activations Density 0.009%

    No Known Activations