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. 15148
    Prev
    Next
    INDEX
    Explanations

    length

    np_max-act-logits · 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
     pulse
    -0.51
    æIJı
    -0.43
    pulse
    -0.41
     Pulse
    -0.41
    èĦī
    -0.40
    è·³
    -0.40
    _pulse
    -0.37
     pul
    -0.37
     beat
    -0.35
     beating
    -0.34
    POSITIVE LOGITS
    .LENGTH
    0.31
    Length
    0.31
     Length
    0.30
     LENGTH
    0.28
     Caller
    0.27
    izza
    0.26
    _length
    0.26
    _Length
    0.26
    length
    0.26
    iza
    0.25
    Activations Density 0.883%

    No Known Activations