© 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. 31863
    Prev
    Next
    INDEX
    Explanations

    want to"}, {"I", "want to"}, {"I", "want"}, {"i", "want"}, {"i", "want to"}

    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»ij稽
    -0.07
    ç»Ŀ
    -0.07
    ulette
    -0.07
    dra
    -0.06
    åĴ½åĸī
    -0.06
    ç¾ŀ
    -0.06
    ieties
    -0.06
    çĶļèĩ³åľ¨
    -0.06
    íĮ
    -0.06
    æľŁæ»¡
    -0.06
    POSITIVE LOGITS
    æĽ´åĸľæ¬¢
    0.09
     kelak
    0.08
     nanti
    0.08
    追éĹ®
    0.08
    åĨįä¾Ĩ
    0.08
     nantinya
    0.08
     later
    0.08
    åħ·ä½ĵéĹ®é¢ĺ
    0.08
     ÙĦاØŃÙĤ
    0.08
    åħ·ä½ĵè¦ģæ±Ĥ
    0.08
    Activations Density 0.008%

    No Known Activations