© 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. 25-TRANSCODER-HP
    7. 108865
    Prev
    Next
    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prime
    -0.31
     technical
    -0.28
    bei
    -0.27
    诸侯
    -0.27
     Prime
    -0.27
    Prime
    -0.27
    ypress
    -0.27
    ["$
    -0.27
    prime
    -0.26
    Ce
    -0.26
    POSITIVE LOGITS
    ä½ĵ积
    0.28
    ç¡®
    0.28
    plates
    0.27
     offending
    0.26
    ouri
    0.26
    à¹Ģà¸Ļ
    0.25
    ouro
    0.25
    è¿ľæĻ¯
    0.24
    ç¼ĸè¾ij
    0.24
    产ä¸ļç»ĵæŀĦ
    0.24
    Activations Density 0.121%

    No Known Activations