© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 56852
    Prev
    Next
    INDEX
    Explanations

    description of prior art

    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
    arks
    -0.08
    è¦ģä¹Īæĺ¯
    -0.07
    ombat
    -0.07
    bole
    -0.07
    argout
    -0.07
    ä¸ĢçĤ¹åĦ¿
    -0.07
    人ä¸į
    -0.07
    reens
    -0.07
     blame
    -0.07
    ENCE
    -0.07
    POSITIVE LOGITS
     disini
    0.08
    大åѦæ¯ķä¸ļ
    0.07
     Insel
    0.07
    pul
    0.07
    asm
    0.07
    æѤç§į
    0.07
    æŀĦæĢĿ
    0.07
    ãĥŀãĤ¬
    0.06
     presently
    0.06
     vul
    0.06
    Activations Density 1.534%

    No Known Activations