© 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. 57496
    Prev
    Next
    INDEX
    Explanations

    Positive or descriptive sentiment

    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
    令人
    -0.30
    æĢª
    -0.29
    éļ¾å¾Ĺ
    -0.28
    ear
    -0.27
    åľ¨æѤ
    -0.26
    å¥ĩæĢª
    -0.26
    antom
    -0.25
     sideline
    -0.25
    iben
    -0.25
    Cool
    -0.24
    POSITIVE LOGITS
     how
    0.42
     How
    0.34
    å¦Ĥä½ķ
    0.33
    How
    0.33
    how
    0.31
    æĺ¯å¦Ĥä½ķ
    0.30
    æĢİæł·
    0.28
    HOW
    0.28
     HOW
    0.26
    ivi
    0.26
    Activations Density 0.017%

    No Known Activations