© 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. 9012
    Prev
    Next
    INDEX
    Explanations

    matrix dimensions (NxN)

    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
    esy
    -0.06
    on
    -0.06
    èī¯å¥½çļĦ
    -0.06
    opes
    -0.06
    appa
    -0.06
    åħĪåIJİ
    -0.06
    alization
    -0.06
    å¿ĥäºĨ
    -0.06
    ault
    -0.06
    à¹ģà¸ģà¹Ī
    -0.06
    POSITIVE LOGITS
    ä¸Ģä½ĵçļĦ
    0.09
    ï¸İ
    0.09
    æľīä½Ļ
    0.08
    /column
    0.08
     ë§Īì°¬
    0.08
    หà¸Ļึà¹Īà¸ĩà¸Ĺีà¹Ī
    0.08
    /from
    0.08
    à¹īà¸Ńม
    0.08
    ç¼Ī
    0.07
    以åĨħçļĦ
    0.07
    Activations Density 0.029%

    No Known Activations