© 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. 53447
    Prev
    Next
    INDEX
    Explanations

    dishes

    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
    .mat
    -0.32
     mat
    -0.30
    mat
    -0.30
    ba
    -0.29
     sin
    -0.27
    retty
    -0.26
    (ir
    -0.26
    ir
    -0.25
    sin
    -0.25
    æ´ĹåĩĢ
    -0.25
    POSITIVE LOGITS
    rams
    0.31
     heaps
    0.26
     asses
    0.26
    ä¸Ĭä¸ĭ
    0.26
    è½½
    0.25
     isLoading
    0.25
    æİ¥
    0.25
    å¤ı天
    0.25
     ''.
    0.25
    ULA
    0.24
    Activations Density 0.009%

    No Known Activations