© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17746
    Prev
    Next
    INDEX
    Explanations

    mutagenic

    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
    zman
    -0.07
    ably
    -0.07
    æĢ§çĸ¾çĹħ
    -0.06
    alde
    -0.06
    achuset
    -0.06
    é¾Ħ
    -0.06
    oplast
    -0.06
    zzi
    -0.06
    жи
    -0.06
    ableObject
    -0.06
    POSITIVE LOGITS
    ness
    0.12
    रण
    0.10
    ities
    0.10
    NESS
    0.10
    ITY
    0.10
    irage
    0.08
    سازÛĮ
    0.08
    ity
    0.08
    nes
    0.08
    å·¥å§Ķ
    0.08
    Activations Density 0.119%

    No Known Activations