© 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. 4283
    Prev
    Next
    INDEX
    Explanations

    safety strains, mutations, reduced biomass

    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
    auen
    -0.07
    ç¿
    -0.07
    aal
    -0.07
    erie
    -0.07
    kab
    -0.07
    ubit
    -0.06
    夺
    -0.06
    tlement
    -0.06
    ADI
    -0.06
    omon
    -0.06
    POSITIVE LOGITS
    ond
    0.07
    µľ
    0.07
    已达
    0.07
    Ñģал
    0.06
    utig
    0.06
    nich
    0.06
    çݲçıij
    0.06
    è¿Ŀåıįä¸Ĭè¿°
    0.06
    ])->
    0.06
    ])[
    0.06
    Activations Density 0.171%

    No Known Activations