© 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. 58088
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    nik
    -0.27
     Managing
    -0.26
    è·¯è¿ĩ
    -0.26
    later
    -0.25
    pu
    -0.25
    åŁł
    -0.24
    è¿ĩ大
    -0.24
    oes
    -0.24
    æ°¸è¿ľ
    -0.24
     commod
    -0.24
    POSITIVE LOGITS
    ä¼łç»ŁçļĦ
    0.40
     instead
    0.37
    ä¼łç»Ł
    0.36
    çļĦä¼łç»Ł
    0.33
     traditional
    0.33
    èĢĮæĺ¯
    0.32
     compared
    0.32
    åĤ³çµ±
    0.30
    CRET
    0.29
     Traditional
    0.29
    Activations Density 0.006%

    No Known Activations