© 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. 39944
    Prev
    Next
    INDEX
    Explanations

    select, essential, panel, round, pulp

    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
    amol
    -0.06
    (loop
    -0.06
    |i
    -0.06
    æªĢ
    -0.06
    даеÑĤÑģÑı
    -0.06
    äºĭäºĭ
    -0.06
    ("^
    -0.06
    ç£Ĭ
    -0.05
    èį·
    -0.05
     su
    -0.05
    POSITIVE LOGITS
    è¦ģä¹Īæĺ¯
    0.10
    è¦ģä¹Ī
    0.09
    imore
    0.08
    ecam
    0.08
    adeiras
    0.08
    ạc
    0.07
     EITHER
    0.07
     enten
    0.07
    çĽ¸å¯¹è¾ĥä½İ
    0.07
    urz
    0.07
    Activations Density 0.061%

    No Known Activations