© 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. 12763
    Prev
    Next
    INDEX
    Explanations

    without *ing

    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
    æ´»åĬ¨æŶ
    -0.08
    åľ¨çĶ¨
    -0.07
    éĹ®é¢ĺæŶ
    -0.07
    ä½ľä¸ļæŶ
    -0.07
    å·¥ä½ľæŶ
    -0.07
     ugyanis
    -0.07
    æĥħåĨµåIJİ
    -0.07
    ä¸įä»ħæľī
    -0.07
    led
    -0.07
     zwar
    -0.07
    POSITIVE LOGITS
    irlo
    0.10
    {/
    0.09
    è¾Ħ
    0.09
    ä»»ä½ķåħ¶ä»ĸ
    0.09
     thereof
    0.08
     necessarily
    0.08
    æģ¼
    0.08
    对åħ¶
    0.08
    ecessarily
    0.08
    ires
    0.08
    Activations Density 0.155%

    No Known Activations