© 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. 42585
    Prev
    Next
    INDEX
    Explanations

    Code and copyright

    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
    æĸ¯é¡¿
    -0.30
    è²Į
    -0.30
    lat
    -0.30
    æĭĽæĶ¶
    -0.26
    tet
    -0.25
    flutter
    -0.25
     Beat
    -0.25
    æ¯ĶæĪij
    -0.25
     lou
    -0.24
     Budd
    -0.24
    POSITIVE LOGITS
    å¥ijæľº
    0.31
    æī©å¼ł
    0.30
    give
    0.30
     empowering
    0.29
    çļĦæľºä¼ļ
    0.28
    çķĻç»Ļ
    0.28
    Give
    0.27
    æĵ´
    0.27
     giving
    0.26
    tight
    0.26
    Activations Density 0.004%

    No Known Activations