© 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. 41242
    Prev
    Next
    INDEX
    Explanations

    documentation section headers

    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
    óra
    -0.08
    å§ij
    -0.07
    ovice
    -0.07
    çĥŃéŨæłĩçŃ¾
    -0.07
    åĶ¯
    -0.07
    ÙİØ°
    -0.07
    oglio
    -0.07
    hausen
    -0.07
    amac
    -0.07
    _LITERAL
    -0.07
    POSITIVE LOGITS
    -*-
    0.07
    æľīæĪIJæķĪ
    0.06
    ulg
    0.06
     -*-
    0.06
    æıIJè¦ģ
    0.06
    getc
    0.06
    åĤĺ
    0.06
    gettext
    0.06
    plements
    0.06
     paras
    0.06
    Activations Density 0.966%

    No Known Activations