© 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. 41800
    Prev
    Next
    INDEX
    Explanations

    renal, dna, lipid, rna, coronary, molecular

    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
    spflicht
    -0.08
    ulumi
    -0.08
    ettor
    -0.07
    spolitik
    -0.07
    zzle
    -0.07
    olat
    -0.07
    Ñīик
    -0.07
    ļĮ
    -0.07
     //~
    -0.07
    panse
    -0.07
    POSITIVE LOGITS
    less
    0.08
    ãĢģ
    0.08
    /
    0.07
    ãĤĦ
    0.07
    lessly
    0.06
    /md
    0.06
    çŃīåħ¶ä»ĸ
    0.06
    æĪĸåħ¶å®ĥ
    0.06
    имо
    0.06
    ì¡°ì°¨
    0.06
    Activations Density 1.369%

    No Known Activations