© 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. 43582
    Prev
    Next
    INDEX
    Explanations

    sports town or team names

    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
    足çIJĥéĺŁ
    -0.07
    ibi
    -0.07
    sequent
    -0.07
    sti
    -0.06
    çĶ¨å®ĥ
    -0.06
    Champ
    -0.06
    æĺ¯åĪĨ
    -0.06
    iru
    -0.06
    vida
    -0.06
    çķ¥
    -0.06
    POSITIVE LOGITS
     defending
    0.08
    bye
    0.08
    papan
    0.08
     defensa
    0.07
    æļĤæĹłæĬ¥ä»·
    0.07
     unlimited
    0.07
    è¿ľå¾ģ
    0.07
     relegated
    0.07
    /misc
    0.07
    CHA
    0.07
    Activations Density 0.215%

    No Known Activations