© 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. 31903
    Prev
    Next
    INDEX
    Explanations

    are here

    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
    odash
    -0.09
    icode
    -0.09
    åħ¬ç½ijå®īå¤ĩ
    -0.08
    ä»»ä½ł
    -0.08
     Redistributions
    -0.08
    odb
    -0.08
    etwork
    -0.08
    ogui
    -0.08
    egie
    -0.08
    creds
    -0.08
    POSITIVE LOGITS
    0.09
    Âł
    0.08
    大åĪ©
    0.07
    âĢ
    0.06
    ³³³³
    0.06
    
    0.06
    1
    0.06
     //{
    0.06
     nonlinear
    0.06
    ³³
    0.06
    Activations Density 2.056%

    No Known Activations