© 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. 18120
    Prev
    Next
    INDEX
    Explanations

    input tag or variable

    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
    ifix
    -0.08
    lacht
    -0.07
    èĢģå¸Ī说
    -0.07
    arre
    -0.07
    _cmp
    -0.07
    æ´½
    -0.06
    个好
    -0.06
    omma
    -0.06
    ieger
    -0.06
    åĩºåı£çļĦ
    -0.06
    POSITIVE LOGITS
    è¾ĵåħ¥
    0.12
     input
    0.11
    input
    0.10
    /input
    0.10
     INPUT
    0.09
     Input
    0.09
    	input
    0.09
    =input
    0.09
    (input
    0.08
    .input
    0.08
    Activations Density 0.457%

    No Known Activations