© 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. 25689
    Prev
    Next
    INDEX
    Explanations

    frequency and scale

    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
    åİļ
    -0.08
    èĥĸ
    -0.08
    æķ¦
    -0.08
    åİļéĩį
    -0.08
    æ²īçĶ¸çĶ¸
    -0.08
    åħ¨çIJĥæľĢ大çļĦ
    -0.08
    æ¿ĥåİļ
    -0.08
    _funcs
    -0.07
    åİļ度
    -0.07
    ä¸ĸçķĮä¸ĬæľĢ大çļĦ
    -0.07
    POSITIVE LOGITS
    ç´°ãģĭãģĦ
    0.09
    å°ĸéĶIJ
    0.08
    (detail
    0.08
    éĭŃ
    0.08
    éĬ³
    0.08
    西åĮ»
    0.08
    fris
    0.08
    å°ĸçļĦ
    0.08
    å°ĸ
    0.08
    (high
    0.08
    Activations Density 0.034%

    No Known Activations