© 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. 57348
    Prev
    Next
    INDEX
    Explanations

    performance

    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
    表达
    -0.28
    Äįe
    -0.28
    åĴ¨è¯¢
    -0.27
    _strip
    -0.26
    èģĺ请
    -0.26
    tha
    -0.25
    æĬ¥
    -0.25
    ban
    -0.24
    æīĩ
    -0.24
    elo
    -0.24
    POSITIVE LOGITS
    æĢ§èĥ½
    0.46
     performance
    0.40
     PERFORMANCE
    0.36
    performance
    0.35
     Performance
    0.33
    Performance
    0.33
     performances
    0.32
    -performance
    0.32
    åĬĽåѦ
    0.32
    _performance
    0.31
    Activations Density 0.046%

    No Known Activations