© 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. 9618
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by a word

    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
    estroy
    -0.08
    å®ī举
    -0.08
    reon
    -0.08
    zed
    -0.08
    igel
    -0.08
    jik
    -0.08
    angat
    -0.08
    tigt
    -0.07
    åħ¬åı·
    -0.07
    .epoch
    -0.07
    POSITIVE LOGITS
    åĽłæѤ
    0.07
     ëĶ°ëĿ¼ìĦľ
    0.07
     therefore
    0.07
    æīĢ以
    0.07
    èĢĮä»ĸ们
    0.06
     verh
    0.06
    磨
    0.06
     so
    0.06
    害
    0.06
    ãģªãģ®ãģ§
    0.06
    Activations Density 0.020%

    No Known Activations