© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 28655
    Prev
    Next
    INDEX
    Explanations

    model identifier or definition

    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
    ¾
    -0.08
    ened
    -0.08
    emberg
    -0.08
    éϵåĮº
    -0.07
    mins
    -0.07
    èĴĻå¾·
    -0.07
    orno
    -0.07
    orney
    -0.07
    ecs
    -0.07
    елей
    -0.07
    POSITIVE LOGITS
    ذج
    0.10
    led
    0.10
    ically
    0.09
    cules
    0.09
    stown
    0.08
    áĥ£áĥłáĥĺ
    0.08
    ateral
    0.08
    ized
    0.08
    ë§ģ
    0.08
    IRROR
    0.08
    Activations Density 0.076%

    No Known Activations