© 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. 55483
    Prev
    Next
    INDEX
    Explanations

    length of string or collection

    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
    ively
    -0.08
    اتÙĩ
    -0.08
    รส
    -0.07
    önen
    -0.07
    LES
    -0.07
    andalone
    -0.06
    leos
    -0.06
    Ñĥне
    -0.06
    sWith
    -0.06
    vera
    -0.06
    POSITIVE LOGITS
    asser
    0.09
    à¯įà®ķ
    0.08
    пеÑĨ
    0.08
    ãģ£ãģĵ
    0.08
    zers
    0.08
    æĸ¯å¡Ķ
    0.08
    Ùij
    0.08
    ÈĽ
    0.08
    AlmostEqual
    0.08
    åľ°äºļ
    0.08
    Activations Density 0.007%

    No Known Activations