© 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. 15600
    Prev
    Next
    INDEX
    Explanations

    yoga, process, entity, capability, parameter, transformation

    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
    çĶ±äºİåħ¶
    -0.08
    luk
    -0.07
    åĽłä¸ºåħ¶
    -0.07
    主è¦ģåİŁåĽłæĺ¯
    -0.07
    indre
    -0.07
    æ¿Ģèį¡
    -0.07
    orni
    -0.07
     Debido
    -0.07
    èĮģ壮
    -0.07
    æĢ§çŃī
    -0.07
    POSITIVE LOGITS
    éĻ
    0.07
    ãģ£ãģ¦ãģĬãĤĬ
    0.07
    .getSelection
    0.07
    åĺĽ
    0.07
    çļĦæĦıæĢĿ
    0.07
    çIJĨ
    0.07
    éĤ¹
    0.07
     erhoben
    0.07
    holz
    0.07
     ê²ĥìĿ´ë©°
    0.06
    Activations Density 0.209%

    No Known Activations