© 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. 37966
    Prev
    Next
    INDEX
    Explanations

    required or recommended

    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
    ptoms
    -0.08
    rš
    -0.08
    åıĪåı¯ä»¥
    -0.08
    è¿ĺ以为
    -0.07
    ä¿®
    -0.07
    PerPage
    -0.07
    apé
    -0.07
    iya
    -0.07
    è¯Ľ
    -0.07
    _allowed
    -0.07
    POSITIVE LOGITS
     mandatory
    0.14
    mandatory
    0.14
     compulsory
    0.13
     mandated
    0.11
     Mandatory
    0.11
     obligatory
    0.11
     oblig
    0.10
     obligatoire
    0.10
     mand
    0.10
     mandates
    0.10
    Activations Density 0.303%

    No Known Activations