© 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. 31046
    Prev
    Next
    INDEX
    Explanations

    like or unlike comparison

    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
    è¯ĿéŁ³
    -0.08
    åľ¨ç»ıè¿ĩ
    -0.08
    åľ¨æŃ¤åŁºç¡Ģä¸Ĭ
    -0.08
    ä¸ĭä¸Ģç§Ĵ
    -0.07
    /products
    -0.07
    éĢĨ
    -0.06
    ä»ħéľĢ
    -0.06
    åĨįæĢİä¹Ī
    -0.06
    å¿»
    -0.06
    第ä¸Ģ天
    -0.06
    POSITIVE LOGITS
    record
    0.08
    æĶ¶å½ķ
    0.08
     Recorded
    0.07
    sci
    0.07
    PARSE
    0.07
     mouseClicked
    0.07
    ired
    0.07
     ç§ģ
    0.07
    è¦ģæī¾
    0.07
     anthology
    0.07
    Activations Density 0.003%

    No Known Activations