© 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. 42649
    Prev
    Next
    INDEX
    Explanations

    source code

    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
    ä¸įåı¯èĥ½
    -0.46
    æĢİä¹Īåı¯èĥ½
    -0.37
     unlikely
    -0.34
    plug
    -0.31
    ä¸įä¼ļæľī
    -0.29
    unlikely
    -0.29
    æĺ¯ä¸įåı¯èĥ½
    -0.29
    æĬľãģij
    -0.28
     likelihood
    -0.28
    çĻ¾åIJĪ
    -0.27
    POSITIVE LOGITS
     highly
    0.59
    ä¸į太
    0.55
     less
    0.55
     Highly
    0.47
    ä¸į大
    0.45
     Less
    0.43
    Less
    0.42
     im
    0.40
     Im
    0.38
    Im
    0.36
    Activations Density 0.002%

    No Known Activations