© 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. 40382
    Prev
    Next
    INDEX
    Explanations

    so followed by clause starters like all, you, the, I, what

    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
    feel
    -0.07
    åħ¶åIJİ
    -0.07
    witter
    -0.07
    piel
    -0.07
    åĩºåħ¶
    -0.07
    éĺ
    -0.07
     ATK
    -0.07
    åįĥç§ĭ
    -0.06
    weather
    -0.06
    äub
    -0.06
    POSITIVE LOGITS
    igno
    0.07
    -ts
    0.07
    çĿ¦
    0.07
    SSIP
    0.06
    åıįæŃ£
    0.06
    idor
    0.06
    è¿Ļå°±æĺ¯æĪij
    0.06
    ign
    0.06
    人çĤº
    0.06
     Moy
    0.06
    Activations Density 0.003%

    No Known Activations