© 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. 30853
    Prev
    Next
    INDEX
    Explanations

    integer overflow issues

    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
    rug
    -0.08
    inach
    -0.08
    ãģ®ãģĭãĤĤãģĹãĤĮ
    -0.08
    ä¹ĭå®Ŀ
    -0.08
    ephir
    -0.08
    fresh
    -0.08
    à®´à¯ģ
    -0.08
    åįģåĪĨéĩįè§Ĩ
    -0.08
    ftar
    -0.08
    mailto
    -0.08
    POSITIVE LOGITS
     safely
    0.08
     safe
    0.07
    åĽ½å®¶å®īåħ¨
    0.07
    Äĥm
    0.07
    é£İéĻ©è¯Ħä¼°
    0.06
    å¨ģåĬĽ
    0.06
    溢åĩº
    0.06
    çļĦå®īåħ¨
    0.06
    å®īåħ¨
    0.06
     unchecked
    0.06
    Activations Density 0.010%

    No Known Activations