© 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. 22402
    Prev
    Next
    INDEX
    Explanations

    pressure or De Blasio or Bee Gees

    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
    æī«æııäºĮç»´çłģä¸ĭè½½
    -0.08
     Adler
    -0.08
    -validate
    -0.08
    errated
    -0.08
    ïs
    -0.08
    åī¯å¤Ħéķ¿
    -0.08
    ÑĦÑĥ
    -0.08
    éĺ²æ°´åį·æĿIJ
    -0.08
    é¡¹çĽ®å¼Ģåıij
    -0.08
    <|box_end|>
    -0.08
    POSITIVE LOGITS
    ç¨ĢéĩĬ
    0.09
     dil
    0.08
    ilt
    0.07
     Effects
    0.07
     effects
    0.07
    å¤ĸéĥ¨
    0.07
    iddy
    0.07
    å¤ĸåĬĽ
    0.07
    ä¸įè¡Į
    0.07
     Dil
    0.06
    Activations Density 0.002%

    No Known Activations