© 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. 107602
    Prev
    Next
    INDEX
    Explanations

    Legal/Technical Context

    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
    GET
    -0.27
    ç¼Ŀ
    -0.26
    .toLocale
    -0.26
    åĪĺæµ·
    -0.26
     cdr
    -0.25
    æ¬ł
    -0.25
    å·´æĸ¯
    -0.25
     ×Ķ×Ĵ
    -0.25
    alia
    -0.24
    åIJĪæł¼
    -0.24
    POSITIVE LOGITS
    èĤ¡ä»½
    0.27
     pelvic
    0.26
    _RF
    0.26
    aż
    0.25
    µ¬
    0.25
    олов
    0.25
    ä¸ĭåĪĹ
    0.24
    owitz
    0.24
     true
    0.24
     authentic
    0.24
    Activations Density 0.902%

    No Known Activations