© 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. 47624
    Prev
    Next
    INDEX
    Explanations

    incoming/outgoing connections

    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
     Ñģобой
    -0.08
    ierung
    -0.07
    è¿ĽéĢĢ
    -0.07
    outers
    -0.07
    大æĪIJ
    -0.07
    æ¨
    -0.06
    çĪ·
    -0.06
    ookies
    -0.06
    ãn
    -0.06
    iated
    -0.06
    POSITIVE LOGITS
    ward
    0.09
    -facing
    0.08
    -only
    0.08
    /up
    0.08
    /down
    0.08
    -active
    0.08
    端çļĦ
    0.08
    /trans
    0.07
    .receive
    0.07
    åĵº
    0.07
    Activations Density 0.069%

    No Known Activations