© 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. 1475
    Prev
    Next
    INDEX
    Explanations

    slight modification or difference

    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
    jenigen
    -0.09
    itale
    -0.09
    ption
    -0.09
    èĩ³å°ij
    -0.08
    elan
    -0.08
    ãĤĴãģĹãģ£ãģĭãĤĬ
    -0.08
    ichel
    -0.08
    -debug
    -0.08
    大åIJī
    -0.08
    εÏį
    -0.08
    POSITIVE LOGITS
    ìĶ©
    0.11
    ãģļãģ¤
    0.10
    ä¹İåħ¶
    0.09
    룬
    0.08
     جدÙĭا
    0.08
    stown
    0.07
    ÙĬ
    0.07
    mente
    0.07
    issime
    0.07
    est
    0.07
    Activations Density 0.012%

    No Known Activations