© 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. 20862
    Prev
    Next
    INDEX
    Explanations

    prepositions related to location or direction

    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
    <|box_end|>
    -0.10
    etheless
    -0.09
    accio
    -0.08
    ä½ķåľ¨
    -0.08
    æĶ¶èĹıæľ¬ç«Ļ
    -0.08
    å§ĭèĩ³ç»Ī
    -0.08
    -than
    -0.08
    écr
    -0.08
    [${
    -0.08
    orso
    -0.08
    POSITIVE LOGITS
    wards
    0.08
    /down
    0.08
    swith
    0.07
     olev
    0.07
    ages
    0.07
    tures
    0.07
    erner
    0.07
    /up
    0.06
    sid
    0.06
    /on
    0.06
    Activations Density 0.608%

    No Known Activations