© 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. 34628
    Prev
    Next
    INDEX
    Explanations

    executing the first step

    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
    å±ĬæŶ
    -0.08
    irman
    -0.08
    oho
    -0.08
    æĮģç»Ńå¼Ģå±ķ
    -0.07
    继ç»ŃåĬªåĬĽ
    -0.07
    æĹ¶èµ·
    -0.07
    reopen
    -0.07
    ä¸įæŃ¢
    -0.07
    ä¾Ľç¨¿
    -0.07
    kens
    -0.07
    POSITIVE LOGITS
     ÙĪÙĤبÙĦ
    0.12
    ä½łåħĪ
    0.09
    å¿ħé¡»åħĪ
    0.08
    åħĪ
    0.08
    åħĪå¾Ĺ
    0.08
    éľĢè¦ģåħĪ
    0.08
    å°±åħĪ
    0.07
    åħĪå°Ĩ
    0.07
    åħĪãģ«
    0.07
    åħĪæĺ¯
    0.07
    Activations Density 0.070%

    No Known Activations