© 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. 17406
    Prev
    Next
    INDEX
    Explanations

    diffusion, excitability, sex, care, drawing, smoking, location, quality, storage, migration

    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
    æĦŁãģ®ãģĤãĤĭ
    -0.08
    สà¹Īวà¸Ļà¸Ĥà¸Ńà¸ĩ
    -0.08
    á»ĩp
    -0.08
    à¹ģรà¸ģà¸Ĥà¸Ńà¸ĩ
    -0.07
    åıijçĶŁåIJİ
    -0.07
    หà¸Ļึà¹Īà¸ĩà¸Ĥà¸Ńà¸ĩ
    -0.07
     pula
    -0.07
    của
    -0.07
    waren
    -0.07
    ureka
    -0.07
    POSITIVE LOGITS
    idio
    0.08
    å½ĵåħ¶
    0.08
    ogat
    0.07
    ieg
    0.07
    agli
    0.07
    使åħ¶
    0.07
    odata
    0.07
    æĪĸåħ¶
    0.07
    intes
    0.07
    oley
    0.07
    Activations Density 0.547%

    No Known Activations