© 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. 63414
    Prev
    Next
    INDEX
    Explanations

    words followed by symbols or values

    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
    roup
    -0.07
    åĽºæľī
    -0.07
    ato
    -0.07
    éĴŁ
    -0.06
    es
    -0.06
    å¸Ń
    -0.06
    èĬ±
    -0.06
    nt
    -0.06
    ä¸Ģåı¥
    -0.06
    ardo
    -0.06
    POSITIVE LOGITS
    lable
    0.09
    caster
    0.08
    utre
    0.08
    RESS
    0.08
    awali
    0.08
    ABILITY
    0.08
    OTES
    0.07
    ña
    0.07
    upplier
    0.07
    _KEYWORD
    0.07
    Activations Density 0.193%

    No Known Activations