© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50074
    Prev
    Next
    INDEX
    Explanations

    after prepositions

    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
    åĪĨåĩº
    -0.07
    ç»
    -0.07
    æīįä¼ļæľī
    -0.07
    ukur
    -0.07
    èĶļ
    -0.07
    kofen
    -0.07
    ắt
    -0.07
     ware
    -0.06
    бай
    -0.06
    ulan
    -0.06
    POSITIVE LOGITS
    ely
    0.08
    opo
    0.07
    Nd
    0.07
    áĥ«
    0.07
    ä¹ĭæīĢ以
    0.07
    éĥ½å¥½
    0.07
    ework
    0.06
    åĨľæŀĹ
    0.06
    vor
    0.06
    nd
    0.06
    Activations Density 0.016%

    No Known Activations