© 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. 3238
    Prev
    Next
    INDEX
    Explanations

    remove punctuation and symbols

    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
    èĢĮä¸įæĺ¯
    -0.08
     plutôt
    -0.07
    rather
    -0.07
     rather
    -0.07
    ÏĢή
    -0.07
    èĢĮéĿŀ
    -0.07
    ä¸İåİŁ
    -0.06
    ebak
    -0.06
    abee
    -0.06
    è¶³å¤Ł
    -0.06
    POSITIVE LOGITS
    éĻ¤æİī
    0.10
     distracting
    0.09
    _extract
    0.09
    éĻ¤åİ»
    0.08
     distr
    0.08
    -remove
    0.08
     Remove
    0.08
     removed
    0.08
    remove
    0.08
    Remove
    0.08
    Activations Density 0.020%

    No Known Activations