© 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. 30375
    Prev
    Next
    INDEX
    Explanations

    updates that

    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
    ood
    -0.08
    egal
    -0.08
    å²ģéĤ£å¹´
    -0.08
    çĻ¾èĪ¬
    -0.08
    egah
    -0.08
    ulty
    -0.07
    amanca
    -0.07
    åįģåĪĨéĩįè¦ģ
    -0.07
    setAttribute
    -0.07
    aved
    -0.06
    POSITIVE LOGITS
    resher
    0.06
    çŃĶæ¡Ī解æŀIJ
    0.06
    _PI
    0.06
    çĭłçĭłçļĦ
    0.06
    è¿Ļä¸ĢåĿĹ
    0.06
    äºĶé¢ľåħŃèī²çļĦ
    0.06
    ､
    0.06
    labs
    0.06
    åIJĦé¡¹çĽ®
    0.06
     Ones
    0.06
    Activations Density 0.034%

    No Known Activations