© 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. 18290
    Prev
    Next
    INDEX
    Explanations

    punctuation and endings

    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
    bie
    -0.08
    æ±ĤçĶŁåŃĺ
    -0.07
    ç¥ĸå¸Ī
    -0.07
    loge
    -0.07
    cott
    -0.07
    ç¥ĸ
    -0.07
    rw
    -0.07
    .feature
    -0.07
    egen
    -0.07
    loyd
    -0.07
    POSITIVE LOGITS
     punctuation
    0.10
    æłĩçĤ¹
    0.09
    ç»Īç»ĵ
    0.09
    åı¥åı·
    0.09
    unctuation
    0.08
    ELS
    0.08
    éĹŃåIJĪ
    0.08
     endings
    0.08
    -ending
    0.08
    å®Įç»ĵ
    0.08
    Activations Density 0.018%

    No Known Activations