© 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. 7538
    Prev
    Next
    INDEX
    Explanations

    purpose of this

    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
    éľĢè¦ģèĢĥèĻij
    -0.08
    mans
    -0.08
     optar
    -0.08
    имÑĥ
    -0.08
    noop
    -0.08
    èµ°åIJijäºĨ
    -0.08
    urgeon
    -0.08
    hver
    -0.08
    acie
    -0.08
     penchant
    -0.07
    POSITIVE LOGITS
    æıIJä¾Ľä¸Ģç§į
    0.10
    æıIJä¾Ľä¸Ģ个
    0.10
    —to
    0.07
    åľ¨äºİ
    0.07
    解åĨ³
    0.07
    建ç«ĭä¸Ģ个
    0.07
    使
    0.07
    æıIJä¾ĽäºĨä¸Ģ个
    0.07
     przede
    0.06
    æľĢ大éĻIJåº¦åľ°
    0.06
    Activations Density 0.205%

    No Known Activations