© 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. 46068
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åį¡æĭī
    -0.08
    妥åĸĦ
    -0.07
    ãĥ£ãĥ³
    -0.07
    ifica
    -0.06
    ¨
    -0.06
    åIJįåĪĹ
    -0.06
    äng
    -0.06
    orea
    -0.06
    angler
    -0.06
    Substring
    -0.06
    POSITIVE LOGITS
    pheres
    0.08
    SEE
    0.08
    à¹ģส
    0.07
    æĤ¦
    0.07
    anity
    0.07
    åĽĽåħŃ级
    0.07
    issi
    0.07
    ÑĮем
    0.07
    è´¢æºIJ
    0.07
    è°§
    0.07
    Activations Density 0.000%

    No Known Activations