© 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. 7537
    Prev
    Next
    INDEX
    Explanations

    review, gameplay, recap

    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
    amps
    -0.08
    oret
    -0.07
    å±¥è¡ĮåIJĪåIJĮ
    -0.07
    mios
    -0.07
     inex
    -0.07
    设æĥ³
    -0.07
    åıªèĥ½è¯´
    -0.07
    öger
    -0.07
    æĥ³è¯´
    -0.06
    icier
    -0.06
    POSITIVE LOGITS
    .orig
    0.07
    å°
    0.07
    .env
    0.07
    пÑĢинима
    0.07
    bbing
    0.07
    ä¸ĭ乡
    0.07
    ough
    0.07
    dep
    0.07
    .deserialize
    0.07
    <O
    0.07
    Activations Density 0.006%

    No Known Activations