© 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. 38400
    Prev
    Next
    INDEX
    Explanations

    High School

    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
    åĭĿè²ł
    -0.06
    rix
    -0.06
     GT
    -0.06
    Mgr
    -0.06
     w
    -0.06
    ignet
    -0.06
     h
    -0.06
    åĩ¶çĮĽ
    -0.06
    dba
    -0.06
    ĵĴ
    -0.06
    POSITIVE LOGITS
    çijŁ
    0.08
    å·
    0.08
    eter
    0.08
    è¿ĺæľīä¸ĢçĤ¹
    0.07
    atl
    0.07
    trim
    0.07
     patolog
    0.07
    çİ°åľ¨è¿ĺ
    0.07
    egro
    0.07
    _OLD
    0.07
    Activations Density 0.079%

    No Known Activations