© 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. 55356
    Prev
    Next
    INDEX
    Explanations

    function names containing action verbs

    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
    ÑĪло
    -0.07
    ↵
    -0.06
    _idxs
    -0.06
    ä¸ĬäºĨ
    -0.06
     |
    -0.06
    apa
    -0.06
    黯
    -0.06
     Dest
    -0.05
    -
    -0.05
    ever
    -0.05
    POSITIVE LOGITS
    '](
    0.09
    ')(
    0.08
    ")(
    0.08
    ","",
    0.08
    æĪIJ羣
    0.08
    ',['
    0.08
    ä¿ĥåıijå±ķ
    0.08
    åĸ°
    0.08
     ÐŁÐ¾Ñħожие
    0.08
    ','',
    0.08
    Activations Density 0.131%

    No Known Activations