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. 23-TRANSCODER-HP
    4. 163257
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    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
    dera
    -0.27
    eties
    -0.25
    _TYPED
    -0.25
    æŃ£ç¢º
    -0.24
    deo
    -0.24
     opportunity
    -0.24
    ή
    -0.24
    tright
    -0.23
    marvin
    -0.23
    .embed
    -0.23
    POSITIVE LOGITS
    å¹²äºĭ
    0.28
    ä»įæľī
    0.28
    uffy
    0.28
    è¡Ģåİĭ
    0.27
     seizures
    0.26
    æ°Ķæģ¯
    0.26
    强度
    0.26
     sometimes
    0.26
     nostr
    0.26
    èĤ¿
    0.26
    Activations Density 0.001%

    No Known Activations