© 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. 21967
    Prev
    Next
    INDEX
    Explanations

    of [word]

    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
    hini
    -0.09
    kaus
    -0.09
    enstein
    -0.08
    [âĢ¦
    -0.08
    (Of
    -0.08
    araus
    -0.08
    ulare
    -0.08
    çĻ¾æĪĺ
    -0.08
    anita
    -0.08
    segue
    -0.08
    POSITIVE LOGITS
     N
    0.06
    /of
    0.06
    thing
    0.06
    ä¿¡æģ¯çŃī
    0.06
     A
    0.06
     thing
    0.05
     dés
    0.05
     possibles
    0.05
     X
    0.05
    ↵
    0.05
    Activations Density 1.413%

    No Known Activations