© 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. 14071
    Prev
    Next
    INDEX
    Explanations

    Rew, frac, el, R, K

    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
    ubil
    -0.08
    |int
    -0.08
    ä¸įæķ¢
    -0.08
    gnore
    -0.07
    zione
    -0.07
    antine
    -0.07
    oin
    -0.07
    ãģĬæ°Ĺ軽
    -0.07
    rint
    -0.07
     sprung
    -0.07
    POSITIVE LOGITS
    ä¸Ģç»Ħ
    0.07
    attel
    0.07
    æį¢
    0.07
    emek
    0.07
    ither
    0.07
    ä¸Ĭä¸ĭ
    0.07
    å¯Į士康
    0.07
    çļĦä¸Ģç»Ħ
    0.07
    ewan
    0.06
     grouped
    0.06
    Activations Density 0.010%

    No Known Activations