© 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. 58619
    Prev
    Next
    INDEX
    Explanations

    obese | mutant | hypertensive | feathering | PTD

    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
    .nih
    -0.07
    常人
    -0.07
    pf
    -0.06
    仿
    -0.06
    éģ¥
    -0.06
     Pes
    -0.06
    åıĸèĪį
    -0.06
    inx
    -0.06
    inh
    -0.06
     Ngo
    -0.06
    POSITIVE LOGITS
    èµĦè´¨
    0.08
    actable
    0.07
    èµĦæł¼çļĦ
    0.07
    aret
    0.07
    -loving
    0.07
    uwe
    0.07
    uhkan
    0.07
    æijĬ
    0.07
    perienced
    0.07
    andal
    0.07
    Activations Density 0.005%

    No Known Activations