© 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. 29312
    Prev
    Next
    INDEX
    Explanations

    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
    lauf
    -0.07
    оÑĢÑĤа
    -0.07
    ationally
    -0.07
    lement
    -0.07
    é¾Ł
    -0.06
     Unt
    -0.06
    ificates
    -0.06
    uments
    -0.06
    quip
    -0.06
    issements
    -0.06
    POSITIVE LOGITS
    Ø©
    0.09
    <|box_end|>
    0.09
    ousel
    0.08
    خداÙħ
    0.07
     vorba
    0.07
    å¸ĪåħĦ
    0.07
    ение
    0.07
    izabeth
    0.07
    adesh
    0.07
    ation
    0.07
    Activations Density 0.021%

    No Known Activations