© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9134
    Prev
    Next
    INDEX
    Explanations

    merino

    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
    ↵↵
    -0.06
    ัà¸į
    -0.06
    åıĤ
    -0.06
    è¿Ļ个éģĵçIJĨ
    -0.06
    <|endoftext|>
    -0.05
    ularity
    -0.05
    sworth
    -0.05
    ç§Ģæīį
    -0.05
    _virtual
    -0.05
    èݽ
    -0.05
    POSITIVE LOGITS
    á»Ńng
    0.08
    ftime
    0.08
    çħĮ
    0.08
    ovil
    0.08
    aterno
    0.07
    éĶ¦æ¶Ľ
    0.07
    scy
    0.07
    kozy
    0.07
    hôtes
    0.07
    沫
    0.07
    Activations Density 0.100%

    No Known Activations