© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44153
    Prev
    Next
    INDEX
    Explanations

    transduction, morbidity, sequelae, conditioned, modulated, lesions, activity

    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
    éģĹçĹĩ
    -0.07
    æľīæĿ¡ä»¶
    -0.07
    ulas
    -0.07
    anka
    -0.06
     Oaks
    -0.06
    izou
    -0.06
    eter
    -0.06
    ition
    -0.06
    ilder
    -0.06
    _categorical
    -0.06
    POSITIVE LOGITS
    "":
    0.08
    RIES
    0.08
    qm
    0.08
    %S
    0.07
    ries
    0.07
    éģĵ人
    0.07
    _charset
    0.07
    fsp
    0.07
    /embed
    0.07
    wm
    0.07
    Activations Density 0.225%

    No Known Activations