© 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. 27959
    Prev
    Next
    INDEX
    Explanations

    danger and panic

    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
     overnight
    -0.08
     evenings
    -0.08
    访
    -0.08
     visits
    -0.07
     Overnight
    -0.07
    éļIJå±ħ
    -0.07
    åģ¶å°Ķ
    -0.07
     subtly
    -0.06
     occasional
    -0.06
     visit
    -0.06
    POSITIVE LOGITS
    æ±ĤçĶŁ
    0.10
    å¥ĭåĬĽ
    0.09
    çĶŁåij½å®īåħ¨
    0.09
    åį±æĢ¥
    0.09
    没æľīåĬŀæ³ķ
    0.09
    æįĤä½ı
    0.09
     adrenaline
    0.09
    ç»ĿæľĽ
    0.09
    æĢ§åij½
    0.09
    åıªèĥ½çĶ¨
    0.09
    Activations Density 0.152%

    No Known Activations