© 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. 30513
    Prev
    Next
    INDEX
    Explanations

    possessive or pronoun followed by verb

    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
    æ£ł
    -0.08
    æ¬
    -0.07
    verläss
    -0.07
    perk
    -0.07
    chnik
    -0.07
    oze
    -0.07
    rette
    -0.07
    æݥ客
    -0.07
    abis
    -0.07
    itting
    -0.07
    POSITIVE LOGITS
    大åĪ©
    0.08
    åħĪçľĭ
    0.07
     Separate
    0.06
    åħĪè¿ĽæĢ§
    0.06
     separate
    0.06
     first
    0.06
    åħĪä»İ
    0.06
    令
    0.06
    Ø°
    0.06
    寧
    0.06
    Activations Density 0.004%

    No Known Activations