© 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. 54286
    Prev
    Next
    INDEX
    Explanations

    apt

    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
    åīª
    -0.30
     clip
    -0.27
    åIJ¸
    -0.25
     Clips
    -0.24
    -END
    -0.24
    çİ»çĴĥ
    -0.24
    åĩºè¡Ģ
    -0.24
    createFrom
    -0.24
     scrub
    -0.24
    æľº
    -0.23
    POSITIVE LOGITS
    itude
    0.29
    entious
    0.29
    imate
    0.29
    ificate
    0.29
    acious
    0.28
    ifier
    0.28
    itary
    0.28
    tee
    0.28
    æĭīæĸ¯
    0.28
    ean
    0.27
    Activations Density 0.010%

    No Known Activations