© 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. 2276
    Prev
    Next
    INDEX
    Explanations

    Continuation, non-volatile, radiographically, endocrine

    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¥ĸå®Ĺ
    -0.07
    বাদ
    -0.06
    ahoo
    -0.06
    irie
    -0.06
    ÅŁa
    -0.06
    ek
    -0.06
     Conserv
    -0.06
    ocos
    -0.06
     Browns
    -0.06
    ablish
    -0.06
    POSITIVE LOGITS
    亦çĦ¶
    0.08
    ä¸įåIJĮçļĦæĺ¯
    0.08
    ä½ľåĪĻ
    0.08
    ziger
    0.08
    åĪĻå°Ĩ
    0.07
    åĪĻ该
    0.07
     hingegen
    0.07
    ezier
    0.07
    enton
    0.07
    æŁ¥çľĭæĽ´å¤ļ
    0.07
    Activations Density 0.017%

    No Known Activations