© 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. 42047
    Prev
    Next
    INDEX
    Explanations

    Laws & Agreements

    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
    æľīæķĪ
    -0.37
    çļĦæľīæķĪ
    -0.35
     effective
    -0.32
     valid
    -0.32
    æľīæķĪçļĦ
    -0.32
    effective
    -0.30
    taking
    -0.30
    	valid
    -0.29
    (valid
    -0.28
     Fus
    -0.28
    POSITIVE LOGITS
    æ±Ĥå©ļ
    0.28
    å®ļä½į
    0.25
    èįī
    0.25
    æĸ¹å¼ıè¿Ľè¡Į
    0.25
    .epam
    0.25
    tÃŃ
    0.25
    è®®
    0.24
    çIJĨ
    0.23
     lic
    0.23
    _heads
    0.23
    Activations Density 0.001%

    No Known Activations