© 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. 50452
    Prev
    Next
    INDEX
    Explanations

    end or to range

    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
    chon
    -0.08
    èĢĮå¤į
    -0.08
    å¤į
    -0.08
    çĪ±å²Ĺ
    -0.07
    igue
    -0.07
    ully
    -0.07
    andel
    -0.07
    .getElement
    -0.07
    ç½®ãģį
    -0.07
    gai
    -0.07
    POSITIVE LOGITS
     inclusive
    0.09
    hack
    0.09
    inclusive
    0.08
    Hack
    0.08
     inclus
    0.07
    Exclusive
    0.07
    ä¸įèĥ½è¶ħè¿ĩ
    0.07
    inclus
    0.07
    åĸľä¹IJ
    0.07
    aderas
    0.07
    Activations Density 0.039%

    No Known Activations