© 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. 9221
    Prev
    Next
    INDEX
    Explanations

    homepage, SAS, scripts

    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
    ADVERTISEMENT
    -0.08
    çŃīä»Ģä¹Ī
    -0.07
    +$
    -0.07
    miss
    -0.07
    çģ«
    -0.06
     &$
    -0.06
    aph
    -0.06
     ÃĤn
    -0.06
    missive
    -0.06
    ::$
    -0.06
    POSITIVE LOGITS
    éĻ¤ä¾Ŀæ³ķé¡»ç»ıæī¹åĩĨçļĦé¡¹çĽ®å¤ĸ
    0.08
    0.08
    ________________________________________________________________
    0.07
    0.07
    0.07
    0.07
    0.07
    ________________________________
    0.07
    0.07
     ................................................................
    0.07
    Activations Density 0.187%

    No Known Activations