© 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. 107411
    Prev
    Next
    INDEX
    Explanations

    comments, code, disclaimers

    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
     hal
    -0.28
    _srv
    -0.27
    hal
    -0.27
    /***/
    -0.26
     Hoy
    -0.26
     outright
    -0.26
     sadd
    -0.25
    мÑĭ
    -0.25
     faithfully
    -0.25
    hou
    -0.25
    POSITIVE LOGITS
    å·¥ä½ľæĸ¹æ¡Ī
    0.25
    ogra
    0.25
    æİ¥çĿĢ
    0.24
    è¾ĵ
    0.24
    جرÙĬ
    0.24
    è°Ł
    0.23
     Democrat
    0.23
    teste
    0.23
    تÙĬÙĨ
    0.22
    dance
    0.22
    Activations Density 0.936%

    No Known Activations