© 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. 57866
    Prev
    Next
    INDEX
    Explanations

    mineral, expression, damage, abuse, communication

    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
    sweise
    -0.08
    edly
    -0.08
    ichten
    -0.08
    人马
    -0.08
    spflicht
    -0.07
    -Compatible
    -0.07
    -peer
    -0.07
     summers
    -0.07
    esz
    -0.07
    ignet
    -0.07
    POSITIVE LOGITS
    æĺ¯æľĢ大çļĦ
    0.07
    -related
    0.07
    缸åħ³çļĦåĨħ容
    0.07
    lder
    0.07
    ä¿¡æģ¯æŁ¥è¯¢
    0.07
    缸åħ³å·¥ä½ľ
    0.07
    缸åħ³çļĦ
    0.06
    æĺ¯æľĢ好çļĦ
    0.06
    è¦ģåħħåĪĨ
    0.06
    -based
    0.06
    Activations Density 0.201%

    No Known Activations