Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 30-TRANSCODER-HP
    4. 15256
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     simult
    -0.29
    omba
    -0.28
    TEE
    -0.26
     ëıĻìĭľ
    -0.26
    PLEMENT
    -0.26
    orning
    -0.25
     detections
    -0.25
    atu
    -0.25
    theory
    -0.25
    atures
    -0.25
    POSITIVE LOGITS
    éĹ¾
    0.29
    åİĨ
    0.28
    eur
    0.26
    çαå¥ĩ
    0.26
     cru
    0.25
    æ·¡æ·¡
    0.25
     higher
    0.24
     zwiÄħzku
    0.24
    æĽ
    0.24
    env
    0.24
    Activations Density 0.874%

    No Known Activations

    This feature has no known activations.