© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17838
    Prev
    Next
    INDEX
    Explanations

    boundary, disk, sphere, compact

    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
    amor
    -0.08
     despe
    -0.08
    ventus
    -0.08
    chie
    -0.07
    æĪIJç«ł
    -0.07
    chant
    -0.07
    tail
    -0.07
    inge
    -0.07
    æĥij
    -0.07
     Perdana
    -0.07
    POSITIVE LOGITS
     inclusive
    0.08
    åİļ
    0.08
    åĮħæĭ¬
    0.08
     endpoints
    0.07
    å§Ķ
    0.07
     including
    0.07
     Includes
    0.07
    å®Įæķ´åľ°
    0.07
    éĹŃåħ³
    0.07
    (compact
    0.07
    Activations Density 0.007%

    No Known Activations