© 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. 33891
    Prev
    Next
    INDEX
    Explanations

    DNA, RNA, genome, replication, editing

    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
    éĶĢ
    -0.07
    atas
    -0.07
    ssen
    -0.06
    ibra
    -0.06
    bra
    -0.06
    çİ°åľ¨æľī
    -0.06
     Thom
    -0.06
    麻
    -0.06
    nels
    -0.06
    èĢĥå¯Ł
    -0.06
    POSITIVE LOGITS
    ryption
    0.08
     stored
    0.08
    è´®åŃĺ
    0.08
    æĭĸçĿĢ
    0.08
    æķĻä½ĵ
    0.07
    CONTENT
    0.07
    è´®
    0.07
    .contentType
    0.07
    è´®èĹı
    0.07
    outdir
    0.07
    Activations Density 0.066%

    No Known Activations