© 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. 3363
    Prev
    Next
    INDEX
    Explanations

    numbers, units, and measurement dimensions

    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
    vou
    -0.08
    çİ®
    -0.08
    è¡·å¿ĥçļĦ
    -0.07
    ä¸Ģå¦Ĥ
    -0.07
    ascade
    -0.07
    çŁŃæļĤçļĦ
    -0.07
    pli
    -0.06
    unden
    -0.06
    ahl
    -0.06
    aday
    -0.06
    POSITIVE LOGITS
    IDI
    0.08
    åĬ¨è¾Ħ
    0.07
    åĩłåįģä¸ĩ
    0.07
    zos
    0.07
    åĩłåįģ
    0.07
     tre
    0.06
    minus
    0.06
     minus
    0.06
    ateg
    0.06
    ridged
    0.06
    Activations Density 0.026%

    No Known Activations