© 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. 46806
    Prev
    Next
    INDEX
    Explanations

    incorporate into

    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
    Ø©
    -0.10
    hafte
    -0.08
    yer
    -0.08
    OrNull
    -0.07
    iers
    -0.07
    eca
    -0.07
    ened
    -0.07
    ness
    -0.07
    -0.07
    heber
    -0.07
    POSITIVE LOGITS
    porate
    0.12
    Into
    0.11
     ÑģÑİда
    0.10
    /embed
    0.10
    è¿Ľåİ»
    0.10
    ments
    0.10
    _into
    0.10
    è¿ĽæĿ¥çļĦ
    0.09
    into
    0.09
     into
    0.09
    Activations Density 0.030%

    No Known Activations