© 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. 7667
    Prev
    Next
    INDEX
    Explanations

    boolean literal `true`

    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
    PIP
    -0.08
    éĻħ
    -0.07
    ä¹İ
    -0.07
    輩
    -0.07
    %!
    -0.06
    oops
    -0.06
    inges
    -0.06
    towe
    -0.06
    西æ´ĭ
    -0.06
    ixo
    -0.06
    POSITIVE LOGITS
    lick
    0.08
    åĪĨä¹ĭ
    0.07
    bred
    0.07
     nevertheless
    0.07
    ider
    0.07
    æīĵæŃ»
    0.07
    å¦ĸåŃ½
    0.07
    aida
    0.07
    uria
    0.07
    ãĥĵãĤ¢
    0.07
    Activations Density 0.026%

    No Known Activations