© 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. 24244
    Prev
    Next
    INDEX
    Explanations

    azoles and azides

    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
    abee
    -0.08
    ëĭ¤ë©´
    -0.07
    å©ķ
    -0.07
    elos
    -0.07
    azzo
    -0.07
    tral
    -0.07
    inius
    -0.07
    _alg
    -0.07
    icios
    -0.07
    omore
    -0.07
    POSITIVE LOGITS
    ayed
    0.08
     slain
    0.08
    åĮĸåIJĪçī©çļĦ
    0.07
    PROP
    0.07
    cxx
    0.07
    Cancelable
    0.07
    çħ§çĽ¸
    0.07
    女éĥİ
    0.06
    æ²īæ²ī
    0.06
    $new
    0.06
    Activations Density 0.025%

    No Known Activations