© 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. 34591
    Prev
    Next
    INDEX
    Explanations

    punctuation and conjunctions followed by labels

    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
    anio
    -0.08
    éĶµ
    -0.07
    ioni
    -0.07
    ings
    -0.07
    æ¸ħæ´ģåīĤ
    -0.06
    è§Ĩç½ij
    -0.06
     MATER
    -0.06
     TÃľ
    -0.06
    etter
    -0.06
    åħľ
    -0.06
    POSITIVE LOGITS
    æĸ°åŀĭåĨłçĬ¶çĹħæ¯ĴæĦŁæŁĵçļĦ
    0.07
    ordat
    0.07
    tit
    0.07
    Advertisement
    0.07
    oggled
    0.07
    Ø©
    0.07
    åį·
    0.07
    çĽĽå¤§çļĦ
    0.07
    det
    0.06
    richtet
    0.06
    Activations Density 0.001%

    No Known Activations