© 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. 62323
    Prev
    Next
    INDEX
    Explanations

    function $f(x)$ definitions and properties

    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
    ate
    -0.08
    ington
    -0.07
    åĬłä¸Ĭ
    -0.06
    åľ¨çĽ®åīį
    -0.06
    INGTON
    -0.06
    æľ«
    -0.06
    è¾ľè´Ł
    -0.06
     volet
    -0.06
    æĥ³æĥ³
    -0.05
    åı¯æĤ²
    -0.05
    POSITIVE LOGITS
    å§ĭèĩ³ç»Ī
    0.10
    RuleContext
    0.09
    æĪijæĿ¥è¯´
    0.08
    Ñģнабжение
    0.08
    è°ģæĿ¥
    0.08
    æķ´åº§
    0.08
    едеÑĢа
    0.08
     ...,
    0.08
    tlement
    0.07
    å¼Ģå¼Ģå¿ĥ
    0.07
    Activations Density 0.008%

    No Known Activations