© 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. 57368
    Prev
    Next
    INDEX
    Explanations

    voting, diagnosis, favor

    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
    wad
    -0.09
    osi
    -0.08
    zeg
    -0.08
    oci
    -0.07
    ostal
    -0.07
    PTY
    -0.07
    ufig
    -0.07
    oca
    -0.07
    andle
    -0.07
    æī¾æī¾
    -0.07
    POSITIVE LOGITS
     favorable
    0.13
     favourable
    0.12
     unfavorable
    0.11
     Favor
    0.10
    åģıåIJij
    0.09
     favor
    0.09
     благопÑĢиÑıÑĤ
    0.09
     favour
    0.08
     fav
    0.08
    åĢ¾åIJijäºİ
    0.08
    Activations Density 0.336%

    No Known Activations