© 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. 7793
    Prev
    Next
    INDEX
    Explanations

    forefront, clustering, coverage, alternative, heterogeneous

    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
    æī©å±ķèµĦæĸĻ
    -0.08
    ¶ļ
    -0.08
    çŃīåħ¶ä»ĸ
    -0.07
    ä¹Łåı«
    -0.07
    eto
    -0.07
    è§Ħå®ļçļĦåħ¶ä»ĸ
    -0.07
    æ´»åĬ¨çŃī
    -0.07
    yre
    -0.06
    çŃīçŃī
    -0.06
    íķĺ기ëıĦ
    -0.06
    POSITIVE LOGITS
    åĩŃåĢŁåħ¶
    0.07
    ิม
    0.07
    >>,
    0.07
    èģĶåIJĪåĪĽå§ĭ人
    0.07
     {{{
    0.07
    ”ØĮ
    0.07
    jian
    0.07
    -hash
    0.07
    acen
    0.07
    spath
    0.07
    Activations Density 0.016%

    No Known Activations