© 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. 27-TRANSCODER-HP
    7. 8760
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aston
    -0.28
    æĪ¿ä¸ľ
    -0.27
    人å¿ĥ
    -0.26
    grades
    -0.26
     Whoever
    -0.26
    ç»ıå¼Ģ
    -0.26
     outweigh
    -0.25
    è¦ģ好好
    -0.25
    makers
    -0.24
    PCS
    -0.24
    POSITIVE LOGITS
     use
    0.44
     using
    0.43
    使çĶ¨
    0.42
    -use
    0.35
    using
    0.35
    Use
    0.35
    .Use
    0.34
    Using
    0.34
     Use
    0.33
    	Use
    0.33
    Activations Density 0.023%

    No Known Activations