© 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. 15091
    Prev
    Next
    INDEX
    Explanations

    variable, fields, camera, page, message, header, endpoint, state

    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
    çļĦéĹ®é¢ĺæĺ¯
    -0.07
    åIJijæĹ¥
    -0.07
    è·¯åĮĹ
    -0.07
    å¦Ĵ
    -0.07
    å²Ń
    -0.07
    çĿIJ
    -0.07
    /address
    -0.07
    å¸Ĥåľºåıijå±ķ
    -0.06
    交éģĵ
    -0.06
    客æĪ·è¦ģæ±Ĥ
    -0.06
    POSITIVE LOGITS
     плÑİÑģ
    0.09
    æľ¬èº«
    0.09
    åĬłä¸Ĭ
    0.09
     minus
    0.09
     itself
    0.09
    's
    0.09
     plus
    0.09
     multiplied
    0.08
    æľ¬èº«çļĦ
    0.08
     ditambah
    0.08
    Activations Density 0.037%

    No Known Activations