© 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. 26423
    Prev
    Next
    INDEX
    Explanations

    vector class usage

    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
    ifel
    -0.08
    zza
    -0.08
    ึà¸ģ
    -0.08
    warzys
    -0.08
    ç½®åľ°
    -0.08
    istic
    -0.08
    brero
    -0.07
    anggar
    -0.07
    jš
    -0.07
    fully
    -0.07
    POSITIVE LOGITS
    ลฯ
    0.10
    ailles
    0.09
    ãĥ³
    0.08
    ãģĬãģĿãĤīãģı
    0.08
    ãĢħãģ®
    0.08
    an
    0.08
    ãģĬäºĴ
    0.07
    اÙĨ
    0.07
    ordia
    0.07
    áĥĺáĥĹ
    0.07
    Activations Density 0.003%

    No Known Activations