© 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. 56378
    Prev
    Next
    INDEX
    Explanations

    latex fraction numerator

    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
    æĢ§çļĦ
    -0.06
    ãĤĵãģ§ãģĻãģŃ
    -0.06
    ingly
    -0.06
    åĽ½å®¶åıijæĶ¹å§Ķ
    -0.06
    å®ģ
    -0.06
     اÙĦÙħØŃا
    -0.06
    ä»ĸçĶ¨
    -0.05
    probe
    -0.05
    ureka
    -0.05
     Serving
    -0.05
    POSITIVE LOGITS
    jsc
    0.09
    ptos
    0.08
     renc
    0.08
    ftime
    0.08
    ä¸Ģå¤ķ
    0.08
    leder
    0.08
    ×ķ×ĺ
    0.08
    éĤ£æĺ¯æĪij
    0.08
    ¸
    0.08
    .Qual
    0.08
    Activations Density 0.014%

    No Known Activations