© 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. 27916
    Prev
    Next
    INDEX
    Explanations

    group theory subgroups

    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
    çīĪåĽ¾
    -0.08
     lợ
    -0.07
    æľīåħ³åįķä½į
    -0.07
    _MACRO
    -0.07
    å¿ĥçĹĽ
    -0.07
     border
    -0.06
     lug
    -0.06
     Cav
    -0.06
     spot
    -0.06
    orie
    -0.06
    POSITIVE LOGITS
     subgroup
    0.08
    nacht
    0.08
    [email
    0.08
    ocken
    0.07
    ×ķ×ĺ
    0.07
     Journals
    0.07
    corev
    0.07
    ledo
    0.07
    çł¥
    0.07
    emma
    0.07
    Activations Density 0.007%

    No Known Activations