© 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. 50557
    Prev
    Next
    INDEX
    Explanations

    circle layouts and geometry

    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
    à¸ģารà¸ĵà¹Į
    -0.11
    Ø©
    -0.09
    ktop
    -0.08
    imizer
    -0.08
    ات
    -0.08
    ively
    -0.08
    OrDefault
    -0.08
    schild
    -0.08
     demikian
    -0.07
    iveness
    -0.07
    POSITIVE LOGITS
    IRCLE
    0.09
    USTOM
    0.09
    OUNTER
    0.08
    wright
    0.08
    ÏĦÏĮ
    0.07
    iphers
    0.07
    culated
    0.07
    valho
    0.07
    liness
    0.07
    ish
    0.07
    Activations Density 0.013%

    No Known Activations