© 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. 61919
    Prev
    Next
    INDEX
    Explanations

    guid followed by colon or comma

    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
    /proto
    -0.09
    ATEN
    -0.09
    irão
    -0.08
     вÑĬÑĢÑħÑĥ
    -0.08
    Einst
    -0.08
    å©·å©·
    -0.08
    Destructor
    -0.08
    (?:
    -0.08
    émon
    -0.07
    omás
    -0.07
    POSITIVE LOGITS
    ing
    0.07
    isit
    0.07
    ä¸Ńé¤IJ
    0.07
    ocha
    0.07
    ://
    0.06
    oo
    0.06
    åģļçĿĢ
    0.06
    uchs
    0.06
    åĦ¿
    0.06
    å¸Ĥåľºåįłæľīçİĩ
    0.06
    Activations Density 0.002%

    No Known Activations