© 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. 40198
    Prev
    Next
    INDEX
    Explanations

    say to specify examples

    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
    æľ¬ç«ĻæīĢæľī
    -0.08
    计ç®Ĺæľºè½¯ç¡¬ä»¶
    -0.08
    以åıĬåľ¨
    -0.07
    ä»»ä½ķè´¹çĶ¨
    -0.07
    以任ä½ķ
    -0.07
    riors
    -0.07
    ender
    -0.07
     Truy
    -0.07
     properly
    -0.07
    Speech
    -0.07
    POSITIVE LOGITS
    é»ĺ
    0.07
    éĢĨ
    0.07
    çļĦåIJ§
    0.07
    ITS
    0.07
    zM
    0.06
    ÙĦاÙĭ
    0.06
    åij½åIJį为
    0.06
    amba
    0.06
    say
    0.06
    esen
    0.06
    Activations Density 0.223%

    No Known Activations