© 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. 17558
    Prev
    Next
    INDEX
    Explanations

    commas and code delimiters

    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
    è¾Ī
    -0.07
    é«ĺé£İéĻ©åľ°åĮº
    -0.07
    "^
    -0.07
    è¨Ģä¹ĭ
    -0.06
    èĤºçĤİçĸ«æĥħ
    -0.06
     improv
    -0.06
    beck
    -0.06
    rm
    -0.06
    uzz
    -0.06
    .await
    -0.06
    POSITIVE LOGITS
    undry
    0.08
    isie
    0.07
    icara
    0.07
     anything
    0.07
    aven
    0.07
    ailable
    0.07
    aved
    0.07
    ingga
    0.06
    estra
    0.06
    près
    0.06
    Activations Density 0.008%

    No Known Activations