© 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. 23540
    Prev
    Next
    INDEX
    Explanations

    very recently

    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
    oki
    -0.08
    çħ§
    -0.07
    cker
    -0.07
     multim
    -0.07
    å½»
    -0.07
    .bio
    -0.06
    affles
    -0.06
    ä»ĵ
    -0.06
    /null
    -0.06
     Denn
    -0.06
    POSITIVE LOGITS
    ä¸Ĭæŀ¶
    0.07
     ë²Ī째
    0.07
    ë²Ī째
    0.07
    èĮģ
    0.07
     ranked
    0.06
    asten
    0.06
    å®ĪåĪĻ
    0.06
    spf
    0.06
    ltre
    0.06
    _unused
    0.06
    Activations Density 0.042%

    No Known Activations