© 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. 53993
    Prev
    Next
    INDEX
    Explanations

    or

    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
     them
    -0.34
     trouble
    -0.30
     him
    -0.29
     vel
    -0.27
    him
    -0.27
     At
    -0.27
    ire
    -0.27
     Ñģебе
    -0.27
     Of
    -0.26
     clinical
    -0.26
    POSITIVE LOGITS
    æĪijæīį
    0.30
    (Be
    0.29
    be
    0.29
    ingo
    0.28
    Be
    0.28
     be
    0.27
    anked
    0.27
    åĩºè½¨
    0.27
     orchestrated
    0.27
    ä¹Łè®¸æĺ¯
    0.27
    Activations Density 0.038%

    No Known Activations