© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12396
    Prev
    Next
    INDEX
    Explanations

    genotype frequencies and proportions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åķ¡
    -0.07
     circuits
    -0.07
     rage
    -0.07
     Reinh
    -0.07
    wok
    -0.07
    延
    -0.07
    RAFT
    -0.06
    deen
    -0.06
    ucid
    -0.06
    วà¸ģ
    -0.06
    POSITIVE LOGITS
    åįłæ¯Ķ
    0.09
     proportions
    0.08
     probabilities
    0.08
    çıĬçıĬ
    0.07
     genotype
    0.07
    _probs
    0.07
     prevalence
    0.07
    Marsh
    0.07
    Probability
    0.07
     ë¹Ħìľ¨
    0.07
    Activations Density 0.003%

    No Known Activations