© 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. 64548
    Prev
    Next
    INDEX
    Explanations

    assuming negative or positive

    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
    ivery
    -0.08
    åħ¬å®³
    -0.08
     -:
    -0.08
    ?p
    -0.07
    æģ©æĥħ
    -0.07
     (::
    -0.07
    arna
    -0.07
     rosk
    -0.07
    /if
    -0.07
    elow
    -0.07
    POSITIVE LOGITS
    rows
    0.06
    es
    0.06
    oj
    0.06
    å¯¹æľ¬æ¬¡
    0.06
     cousins
    0.06
     Gree
    0.06
    åħ¶ä¸ŃçļĦ
    0.06
    ar
    0.06
    该项
    0.06
    uteurs
    0.06
    Activations Density 0.003%

    No Known Activations