© 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. 22058
    Prev
    Next
    INDEX
    Explanations

    minutes

    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
    arrer
    -0.08
    ostr
    -0.07
    éĵºè®¾
    -0.07
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    -0.07
    顾åIJįæĢĿä¹ī
    -0.07
    æŁł
    -0.07
    èĩªåѦèĢĥè¯ķ
    -0.07
    ascin
    -0.07
     Setter
    -0.07
    á»ĩ
    -0.07
    POSITIVE LOGITS
    éĩįè¦ģçļĦæĺ¯
    0.08
    ä½Ĩè¦ģ
    0.08
    çĶļèĩ³
    0.07
    çĶļèĩ³åı¯ä»¥
    0.07
    Alternative
    0.07
    åħ¹
    0.07
     Alternatively
    0.07
    аÑĤо
    0.07
    åı¦
    0.07
    ç¦ıå¾·
    0.07
    Activations Density 0.024%

    No Known Activations