© 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. 61626
    Prev
    Next
    INDEX
    Explanations

    B followed by Experience, tab, or Found

    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
    åŃIJæĽ°
    -0.06
    å¥ļ
    -0.06
    leist
    -0.06
    ÛĮزÛĮ
    -0.06
    vky
    -0.06
     Loaded
    -0.06
    opf
    -0.06
    elo
    -0.06
    hof
    -0.06
    ützen
    -0.06
    POSITIVE LOGITS
    åĭĩå¾Ģ缴åīį
    0.08
    ucker
    0.08
    ellone
    0.08
    acco
    0.07
    olini
    0.07
    rido
    0.07
    ffen
    0.07
    omma
    0.07
    åIJĪåIJĮæŶ
    0.07
    -fly
    0.07
    Activations Density 0.240%

    No Known Activations