© 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. 33954
    Prev
    Next
    INDEX
    Explanations

    Names starting with specific syllables

    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
    æijĴ
    -0.08
    è¹Ī
    -0.07
    ces
    -0.07
    ¬
    -0.06
    æĨ¾
    -0.06
    umm
    -0.06
    以ä¸Ģ
    -0.06
    sid
    -0.06
    è¹Ĥ
    -0.06
     Manson
    -0.06
    POSITIVE LOGITS
    BitFields
    0.08
     terbak
    0.08
    OffsetTable
    0.08
    lán
    0.08
    bert
    0.08
     melew
    0.07
    æľ¬ç§ij以ä¸ĬåѦåİĨ
    0.07
     degusta
    0.07
    NEXT
    0.07
    bjerg
    0.07
    Activations Density 0.811%

    No Known Activations