© 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. 27700
    Prev
    Next
    INDEX
    Explanations

    navigation menu

    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
    (|
    -0.08
    verständlich
    -0.07
    å·²ç»ı被
    -0.07
    大æĤ²
    -0.07
    ÑĢид
    -0.07
    amai
    -0.07
    _annotations
    -0.07
    wit
    -0.07
    .omg
    -0.06
    è§Ħå®ļ
    -0.06
    POSITIVE LOGITS
    çĭIJ
    0.07
    .chars
    0.07
    ç§Ģ
    0.07
    upsi
    0.07
    æ±²
    0.07
    天ä¸ĭ
    0.07
    çĸ½
    0.07
    æķ¦
    0.07
    zeÅĽ
    0.07
    nty
    0.06
    Activations Density 0.001%

    No Known Activations