© 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. 61872
    Prev
    Next
    INDEX
    Explanations

    NONPRECEDENTIAL, disposition

    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
    çĵ¦
    -0.07
    jada
    -0.07
    iva
    -0.07
    é¼ĵ
    -0.07
    ä¸į妨
    -0.07
    æīĢ欲è¨Ģ
    -0.07
    _APB
    -0.07
    isia
    -0.07
    iba
    -0.07
    миÑĢа
    -0.07
    POSITIVE LOGITS
    /net
    0.08
    éĹ»è¨Ģ
    0.07
    kaar
    0.07
     simul
    0.07
    çģĺ
    0.07
    ujuh
    0.06
    ADV
    0.06
    erlo
    0.06
    éģĩåĪ°éĹ®é¢ĺ
    0.06
    nets
    0.06
    Activations Density 0.003%

    No Known Activations