© 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. 33903
    Prev
    Next
    INDEX
    Explanations

    gender, name, Se, area, quarterback, user

    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
     t
    -0.06
    got
    -0.06
    -0.06
    aland
    -0.06
    è¡ħ
    -0.06
     Ho
    -0.06
    <|fim_suffix|>
    -0.05
    ibas
    -0.05
    Side
    -0.05
     заÑĢа
    -0.05
    POSITIVE LOGITS
    ạch
    0.09
    abcdefgh
    0.09
    iros
    0.08
    ÄįiÄĩ
    0.08
    ujan
    0.08
    truk
    0.08
    aben
    0.08
    ELY
    0.08
     **¿
    0.08
    å°½ãģı
    0.08
    Activations Density 0.180%

    No Known Activations