© 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. 32-TRANSCODER-HP
    7. 41269
    Prev
    Next
    INDEX
    Explanations

    only

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nt
    -0.28
    æīĢè¿°
    -0.26
     More
    -0.26
    .toDouble
    -0.26
    æĢĢ
    -0.25
     clearly
    -0.25
    两æīĭ
    -0.25
     more
    -0.25
    好å¤ļ
    -0.25
    More
    -0.24
    POSITIVE LOGITS
     ever
    0.60
    -ever
    0.54
     EVER
    0.52
    ä»»ä½ķ
    0.52
    ever
    0.48
    any
    0.41
     Ever
    0.40
     any
    0.40
    Ever
    0.38
    ä»»ä½ķ人
    0.38
    Activations Density 0.003%

    No Known Activations