© 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. 65099
    Prev
    Next
    INDEX
    Explanations

    question/answer pairs

    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
    etti
    -0.08
    ÐŃС
    -0.08
    åıĬæĹ¶æ²»çĸĹ
    -0.08
    Ĺı
    -0.08
    ÑģÑģоÑĢа
    -0.08
    коло
    -0.07
    åĽłåľ°
    -0.07
    ylvania
    -0.07
    accion
    -0.07
    gies
    -0.07
    POSITIVE LOGITS
    eway
    0.07
    /
    0.06
    isant
    0.06
    .exports
    0.06
    aved
    0.06
    涵
    0.06
    åĪ¶
    0.06
    sh
    0.06
    ih
    0.06
    è¡£
    0.06
    Activations Density 0.023%

    No Known Activations