© 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. 17158
    Prev
    Next
    INDEX
    Explanations

    spectroscopy and analysis methods

    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
    è£
    -0.07
    _DA
    -0.06
    ä¸ĢåĪ°
    -0.06
    æĪijæĿ¥è¯´
    -0.06
    彦
    -0.06
     scha
    -0.06
    è§ģå¾Ĺ
    -0.06
    åıĪæľī
    -0.06
    éĶĻèIJ½
    -0.06
    æī«åľ°
    -0.06
    POSITIVE LOGITS
    å¾Ĺ天çĭ¬
    0.08
     Studio
    0.08
    gnore
    0.07
    Studio
    0.07
    ä¿ĬæĿ°
    0.07
    åĨ·çļĦ
    0.07
    ãģ¬
    0.07
    raub
    0.07
    aseline
    0.07
    studio
    0.07
    Activations Density 0.089%

    No Known Activations