© 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. 60300
    Prev
    Next
    INDEX
    Explanations

    array argument a CIF parameter

    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
    滩
    -0.07
    家éŨ
    -0.07
    ema
    -0.07
     DISCLAIMER
    -0.06
     rud
    -0.06
    ern
    -0.06
    attle
    -0.06
    ¤
    -0.06
    opoulos
    -0.06
    enne
    -0.06
    POSITIVE LOGITS
    å¡«åħ¥
    0.09
    ä¸Ģæł¼
    0.09
    cif
    0.08
    åĽŀå¡«
    0.08
    æ¢Ń
    0.08
    CIF
    0.08
    å¼Ħ
    0.08
    ίδ
    0.08
    _filled
    0.08
    ParameterValue
    0.07
    Activations Density 0.033%

    No Known Activations