© 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. 46049
    Prev
    Next
    INDEX
    Explanations

    underlying reasons or explanations

    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
    unct
    -0.08
    obiet
    -0.08
    acus
    -0.08
    skal
    -0.08
    åī§æ¯Ĵ
    -0.08
    BOSE
    -0.08
    bogen
    -0.07
    avra
    -0.07
    UCT
    -0.07
    ollapsed
    -0.07
    POSITIVE LOGITS
    åİŁåĽł
    0.16
    è¿Ļæĺ¯åĽłä¸º
    0.15
    æĺ¯åĽłä¸º
    0.15
     reasons
    0.15
    为ä»Ģä¹Īä¼ļ
    0.15
    çļĦåİŁåĽł
    0.14
     reason
    0.14
    åİŁåĽłæĺ¯
    0.14
    è¿Ļæĺ¯çĶ±äºİ
    0.14
     underlying
    0.13
    Activations Density 0.288%

    No Known Activations