© 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. 23830
    Prev
    Next
    INDEX
    Explanations

    rewrite rules and conditions

    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
    __$
    -0.09
    velle
    -0.08
    berra
    -0.08
    mith
    -0.08
    kasten
    -0.08
    ëŁŃ
    -0.08
    halter
    -0.08
    ĵ¨
    -0.08
    æ£ĢæŁ¥ç»Ħ
    -0.07
    人èĥ½
    -0.07
    POSITIVE LOGITS
    ä¸Ģèĩ³
    0.06
    F
    0.06
    D
    0.06
     Wander
    0.05
    R
    0.05
    å¾ĹçĽĬ
    0.05
     S
    0.05
    è¿ĻæŶçļĦ
    0.05
     sorry
    0.05
     param
    0.05
    Activations Density 0.066%

    No Known Activations