© 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. 30574
    Prev
    Next
    INDEX
    Explanations

    programming concepts

    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
     Heidel
    -0.08
    åħijç¾İåħĥ
    -0.08
    uckland
    -0.08
    Abs
    -0.07
     *:
    -0.07
    cej
    -0.07
    麾ä¸ĭ
    -0.07
     Gep
    -0.07
    å½ĵåľ°æŶéĹ´
    -0.07
    gel
    -0.07
    POSITIVE LOGITS
    sic
    0.07
    ç¦ģ
    0.07
    çŃīåħ¶ä»ĸ
    0.07
    ily
    0.07
    çĽĪ
    0.06
    çŃīçī¹æ®Ĭ
    0.06
    [++
    0.06
    éĻ¤å¤ĸ
    0.06
    kata
    0.06
    æĺĻ
    0.06
    Activations Density 0.007%

    No Known Activations