© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39440
    Prev
    Next
    INDEX
    Explanations

    database or code formatting

    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
    esz
    -0.08
    æľĪåĩºçĶŁ
    -0.07
    arcz
    -0.06
    èĶij
    -0.06
    æī«æııä¸ĭæĸ¹äºĮç»´çłģ
    -0.06
     incapac
    -0.06
     memor
    -0.06
     imm
    -0.06
     pseudo
    -0.06
     Wich
    -0.06
    POSITIVE LOGITS
    wald
    0.08
    å°±éĤ£ä¹Ī
    0.08
    åıijå±ķæĶ¹éĿ©
    0.08
    iserie
    0.08
    èĬ
    0.07
    éĥ½æľīåı¯èĥ½
    0.07
     Äĩ
    0.07
    äºijå±±
    0.07
    odont
    0.07
    亦æĪĸæĺ¯
    0.07
    Activations Density 0.004%

    No Known Activations