© 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. 26036
    Prev
    Next
    INDEX
    Explanations

    zone, pregnancy, Masters, phones, plans, States, watch

    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
    ç¥ŀè¯Ĩ
    -0.08
    quip
    -0.07
    lad
    -0.06
    åİŁåľ°
    -0.06
    çIJĨæīĢ
    -0.06
    åĸĭ
    -0.06
    ivery
    -0.06
    rael
    -0.06
    ä¸Ĭåı¤
    -0.06
     */,
    -0.06
    POSITIVE LOGITS
    çŃīçī¹æ®Ĭ
    0.20
    çī¹æ®ĬæĢ§
    0.13
     special
    0.13
    çļĦçī¹æ®Ĭ
    0.13
    æľīçī¹æ®Ĭ
    0.13
    çī¹æ®Ĭ
    0.13
    çī¹æ®ĬçļĦ
    0.12
     especiales
    0.12
    åĴĮæĻ®éĢļ
    0.11
    ä¸İæĻ®éĢļ
    0.11
    Activations Density 0.195%

    No Known Activations