© 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. 10396
    Prev
    Next
    INDEX
    Explanations

    motivations and reasons

    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
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    -0.08
    æĪijçļĦç¥Ŀç¦ı
    -0.07
    uhe
    -0.07
    -Language
    -0.07
    ä½łåĪ°åºķ
    -0.07
    çĻ¾åº¦ç½ijçĽĺ
    -0.07
    ocab
    -0.07
    çĶ¨æ¸ħæ°´
    -0.07
    ihi
    -0.07
    Directions
    -0.07
    POSITIVE LOGITS
    å¥ijæľº
    0.10
    è¿ĻäºĽåĽłç´ł
    0.10
     factors
    0.10
    å¸ĤåľºéľĢæ±Ĥ
    0.09
    åĽłç´ł
    0.09
     opportun
    0.09
     desire
    0.09
    çļĦåĽłç´ł
    0.08
    å½ĵæŶçļĦ
    0.08
     reasons
    0.08
    Activations Density 0.129%

    No Known Activations