© 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. 19851
    Prev
    Next
    INDEX
    Explanations

    less followed by adjectives

    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
    endencies
    -0.09
     ulang
    -0.09
    hund
    -0.09
    ozo
    -0.09
    illos
    -0.08
    à¥įत
    -0.08
    abic
    -0.08
    ä¸įæĹ©
    -0.08
    uera
    -0.08
    ç½ijå°ıç¼ĸ
    -0.08
    POSITIVE LOGITS
    -than
    0.16
    ened
    0.14
    ening
    0.14
    _than
    0.13
     than
    0.12
    mals
    0.10
     بÙĥØ«ÙĬر
    0.09
    s
    0.08
    than
    0.08
    ThanOr
    0.08
    Activations Density 0.030%

    No Known Activations