© 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. 9000
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by nouns

    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
    EDO
    -0.06
    ered
    -0.06
    åĩ¡
    -0.06
    ted
    -0.06
    çĶ²éª¨
    -0.06
    åı²ä¸Ĭ
    -0.06
    ä¸ĸä¸Ĭ
    -0.06
    çĶ±åħ¶
    -0.06
    nal
    -0.06
    åİ»å¤Ħ
    -0.06
    POSITIVE LOGITS
    STANCE
    0.08
     здÑĸ
    0.08
    ippines
    0.08
    jali
    0.07
    asilan
    0.07
    å¬Ľ
    0.07
    伦å¤ļ
    0.07
    REEN
    0.07
    ä¸Ń央åĮº
    0.07
    обе
    0.07
    Activations Density 1.460%

    No Known Activations