© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57026
    Prev
    Next
    INDEX
    Explanations

    review of cases

    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
    模
    -0.07
    å¸ĥæľĹ
    -0.06
    åĵĹ
    -0.06
    chon
    -0.06
    ç²
    -0.06
    çĨ
    -0.06
    /release
    -0.06
     mod
    -0.06
    _RESPONSE
    -0.06
     cil
    -0.06
    POSITIVE LOGITS
     retrospect
    0.10
     casos
    0.09
     cases
    0.09
     Cases
    0.09
     ÑģлÑĥÑĩаи
    0.08
    æĶ¶æ²»
    0.08
     retrospective
    0.08
     Valve
    0.08
    Cases
    0.08
     clinic
    0.08
    Activations Density 3.964%

    No Known Activations