© 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. 20169
    Prev
    Next
    INDEX
    Explanations

    characteristic rank

    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
    ä»Ģä¹Īéĥ½
    -0.08
     itulah
    -0.07
    åĨĻ羣ãģ¯
    -0.07
    å½ĵçĦ¶
    -0.07
    åı¯æĺ¯
    -0.07
    è¦ģæĪij
    -0.06
    è¯Ŀ
    -0.06
    æĸ¹æ³ķãģ¯
    -0.06
    çļĦèĦ¸ä¸Ĭ
    -0.06
    è¦ģä¹Ī
    -0.06
    POSITIVE LOGITS
    æĥħåĨµåIJİ
    0.12
     ourselves
    0.11
     versus
    0.10
    çļĦæŶåĢĻäºĨ
    0.10
    éĹ®é¢ĺæŶ
    0.10
     myself
    0.10
     ÑģледÑĥÑİÑīим
    0.10
     anhand
    0.10
    çĦ¶åIJİæĬĬ
    0.09
     ÙĪÙĥÙĬÙģ
    0.09
    Activations Density 0.020%

    No Known Activations