© 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. 21479
    Prev
    Next
    INDEX
    Explanations

    code declarations and values

    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
    ohn
    -0.07
    erm
    -0.07
    çī
    -0.07
    erot
    -0.07
    omos
    -0.07
    .pivot
    -0.06
    ³³
    -0.06
     ere
    -0.06
    er
    -0.06
    hn
    -0.06
    POSITIVE LOGITS
    åĢįçļĦ
    0.08
    agle
    0.08
    æĪijéĤ£
    0.08
    ingleton
    0.08
    akis
    0.07
    ä»Ģä¹Īéĥ½
    0.07
    èĩªçĦ¶èĢĮ
    0.07
    ä½ĵçļĦ
    0.07
    éĤ£ä»½
    0.07
    yar
    0.07
    Activations Density 0.229%

    No Known Activations