© 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. 34486
    Prev
    Next
    INDEX
    Explanations

    code block structure

    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
    éĤ£æŶ
    -0.08
    nock
    -0.08
     Haram
    -0.08
    è®°å¿ĨçĬ¹
    -0.08
    Ĩł
    -0.08
     à¤Ńर
    -0.08
    ä¸įå¹²
    -0.07
    å®īåħ¨åı¯éĿł
    -0.07
    zione
    -0.07
    éħĴ楼
    -0.07
    POSITIVE LOGITS
    åħĪ
    0.08
    ainter
    0.07
    AMI
    0.06
    кÑĤо
    0.06
    è¨Ģ
    0.06
    ÙĪÙĬا
    0.06
    Instr
    0.06
    åħĪåİ»
    0.06
    ä½ľæ³ķ
    0.06
    amy
    0.06
    Activations Density 0.016%

    No Known Activations