© 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. 33969
    Prev
    Next
    INDEX
    Explanations

    effectiveness of

    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
    ê¹IJ
    -0.10
    åħ¢åħ¢ä¸ļä¸ļ
    -0.08
    etat
    -0.08
    thinkable
    -0.08
    araf
    -0.08
    fertig
    -0.08
     Terl
    -0.08
    fert
    -0.08
    denken
    -0.08
    orthy
    -0.08
    POSITIVE LOGITS
    iveness
    0.10
    æľīæķĪçļĦ
    0.08
    -looking
    0.08
    fully
    0.08
    aper
    0.07
    -eff
    0.07
    ä¸İåIJ¦
    0.07
     samping
    0.07
    fect
    0.07
    çİĩçļĦ
    0.07
    Activations Density 0.062%

    No Known Activations