© 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. 47736
    Prev
    Next
    INDEX
    Explanations

    reporting verbs after quotes

    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
    .beta
    -0.08
    arco
    -0.08
    elt
    -0.07
    _utf
    -0.07
    à¦Łà¦¾
    -0.07
    /wp
    -0.07
    @Web
    -0.07
    æ¡£
    -0.07
    सर
    -0.07
    åħ±åº¦
    -0.07
    POSITIVE LOGITS
    ev
    0.07
    çŀ°
    0.06
    upert
    0.06
    åĨĻéģĵ
    0.06
    UMENT
    0.06
     Preg
    0.06
     wrote
    0.06
     accord
    0.06
     porad
    0.06
    ed
    0.06
    Activations Density 0.065%

    No Known Activations