© 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. 29666
    Prev
    Next
    INDEX
    Explanations

    code comment syntax

    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
    -0.10
    yard
    -0.09
    ÑīноÑģÑĤÑĮ
    -0.08
    eli
    -0.08
    åħļå§Ķåī¯ä¹¦è®°
    -0.08
    åĪ©äºļ
    -0.08
    åħļå§Ķå§Ķåijĺ
    -0.08
    ois
    -0.07
    alan
    -0.07
    ijn
    -0.07
    POSITIVE LOGITS
    åħ¶äºĭ
    0.08
    öm
    0.07
     ÙĢÙĢ
    0.06
     henne
    0.06
    пÑĤа
    0.06
    ryp
    0.06
    ABS
    0.06
    epe
    0.06
    TASK
    0.06
    æ®Ĭ
    0.06
    Activations Density 0.003%

    No Known Activations