© 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. 45323
    Prev
    Next
    INDEX
    Explanations

    technical or code terms

    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
    为载ä½ĵ
    -0.07
    sted
    -0.07
    æĪĸåħ¶å®ĥ
    -0.07
    zuki
    -0.07
    سÙĪب
    -0.07
    æĬķèµĦæĪĸ
    -0.07
    æĪĸåĪ©çĶ¨
    -0.07
    èĭį
    -0.07
    vaart
    -0.06
    ä¹ĺæľº
    -0.06
    POSITIVE LOGITS
    çŃīåŁºæľ¬
    0.07
     meticulously
    0.07
    alz
    0.07
    -ste
    0.07
    dont
    0.07
    sic
    0.07
    ä»Ģä¹ĪçļĦ
    0.07
    çŃīæĬĢæľ¯
    0.07
    èŃ²
    0.07
    ìľ¨
    0.06
    Activations Density 0.270%

    No Known Activations