© 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. 21220
    Prev
    Next
    INDEX
    Explanations

    match words or phrases

    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
    åĬłåħ³æ³¨
    -0.08
    ÑĤÑĢÑĥ
    -0.07
    rake
    -0.07
    缴è§Ĩ
    -0.07
    åıijåĶ®
    -0.07
    onn
    -0.06
    ë¡Ŀ
    -0.06
    ldr
    -0.06
    缸è¾ĥ
    -0.06
    æ§IJ
    -0.06
    POSITIVE LOGITS
    åĮ¹éħį
    0.09
     Assigned
    0.09
     Match
    0.09
    æŃ£ç¡®ä½¿çĶ¨
    0.09
     match
    0.09
    Match
    0.08
    è°ľ
    0.08
     assign
    0.08
    assigned
    0.08
     correctly
    0.08
    Activations Density 0.006%

    No Known Activations