© 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. 2193
    Prev
    Next
    INDEX
    Explanations

    Valentine Rene

    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
    λά
    -0.07
    çĽij
    -0.06
    åŁºç¡ĢæĢ§
    -0.06
    oret
    -0.06
     vastly
    -0.06
     flick
    -0.06
     shards
    -0.06
    atter
    -0.06
     Sachs
    -0.06
    è§Ĵè´¨
    -0.06
    POSITIVE LOGITS
    å¦ĤåĽ¾æīĢ示
    0.09
    urez
    0.09
    å·¥ç¨ĭç³»
    0.09
    eri
    0.08
    ảy
    0.08
    åĽ¾ä¸ŃçļĦ
    0.08
    æĶ¯æī¿
    0.08
    hiba
    0.08
    uyết
    0.08
    lesa
    0.08
    Activations Density 0.010%

    No Known Activations