© 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. 41241
    Prev
    Next
    INDEX
    Explanations

    details, maximisation, rotor brakes, Joyce, weight, punk, resources, peace, travel, dispenser

    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
    åİĨ
    -0.07
    اعدة
    -0.07
    upro
    -0.06
    udur
    -0.06
    alin
    -0.06
    沸
    -0.06
     Liter
    -0.06
    ige
    -0.06
    踩è¿ĩ
    -0.06
    çijĻ
    -0.06
    POSITIVE LOGITS
    âĢİ
    0.07
    pha
    0.07
    zek
    0.07
    _Reference
    0.07
    çıįçıł
    0.07
    porta
    0.07
    æ±Łå¸Ĥ
    0.07
    çĸĻçĺ©
    0.07
    ç³ķ
    0.07
    rome
    0.07
    Activations Density 0.458%

    No Known Activations