© 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. 11598
    Prev
    Next
    INDEX
    Explanations

    action leading to a result

    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
    æĹłæĢ¨
    -0.08
    ffin
    -0.08
    è¿ĺè®°å¾Ĺ
    -0.08
     éppen
    -0.08
    elow
    -0.07
    æĥħä¸įèĩªç¦ģ
    -0.07
    è¶Ĭæĥ³
    -0.07
    çĿ¡çĿĢäºĨ
    -0.07
    åĪĽéĢłæĿ¡ä»¶
    -0.07
    è¶Ĭèµ°
    -0.07
    POSITIVE LOGITS
    ä»İæѤ
    0.12
     thereafter
    0.11
    èĩªæѤ
    0.11
    ä»İéĤ£
    0.11
    åĨįä¹Łæ²¡æľī
    0.10
    ä¸Ģæ°Ĺãģ«
    0.10
    åĨįæĹł
    0.09
    æѤåIJİ
    0.09
    ä¸Ģä¸ĭåŃIJ
    0.09
    é¡¿æŶ
    0.09
    Activations Density 0.396%

    No Known Activations