© 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. 20816
    Prev
    Next
    INDEX
    Explanations

    author attribution

    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
     Forbes
    -0.06
    æľ¬ç¯ĩæĸĩç«ł
    -0.05
    å±ħä¸Ń
    -0.05
    äºıäºĨ
    -0.05
     concerned
    -0.05
     Apl
    -0.05
    pf
    -0.05
    ...
    -0.05
    ä»İä¸Ĭ
    -0.05
    -0.05
    POSITIVE LOGITS
    ostro
    0.09
    ç·£
    0.09
    åĬ
    0.08
    идÑĥ
    0.08
    ç©«
    0.08
    chenkt
    0.08
    attachment
    0.08
    éįĬ
    0.08
    馴
    0.08
    ODEV
    0.08
    Activations Density 0.001%

    No Known Activations