© 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. 43850
    Prev
    Next
    INDEX
    Explanations

    contributing

    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
    æļĤè¡ĮåĬŀæ³ķ
    -0.09
    omp
    -0.08
    odz
    -0.08
    avra
    -0.08
    óc
    -0.08
    è¦ģæĮīçħ§
    -0.08
    umfang
    -0.08
     заÑĤо
    -0.08
    è¡·å¿ĥçļĦ
    -0.07
    éĥ½è¡¨ç¤º
    -0.07
    POSITIVE LOGITS
     contributing
    0.14
     contribution
    0.14
    contrib
    0.14
     contributes
    0.14
     contrib
    0.13
     contribute
    0.13
     contributed
    0.13
    æĺ¯å¯¼èĩ´
    0.12
     contribu
    0.12
     Contrib
    0.12
    Activations Density 0.349%

    No Known Activations