© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 27074
    Prev
    Next
    INDEX
    Explanations

    caries, cervix, resonance

    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
    zzle
    -0.09
    ycin
    -0.09
    aner
    -0.08
    mej
    -0.08
    åį«ä¸ľ
    -0.08
    бÑĢи
    -0.08
    teni
    -0.08
    anee
    -0.08
    lyph
    -0.08
     gjerne
    -0.08
    POSITIVE LOGITS
    0.06
    imb
    0.06
    0.06
    ↵
    0.06
     imb
    0.06
     Tho
    0.05
    ç¹ģ
    0.05
     cons
    0.05
    гÑĭ
    0.05
    å»·
    0.05
    Activations Density 1.571%

    No Known Activations