© 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. 47169
    Prev
    Next
    INDEX
    Explanations

    list parameters

    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
    levant
    -0.07
    porno
    -0.07
    loff
    -0.07
     Gaw
    -0.07
    nikov
    -0.07
    uetype
    -0.07
    /pdf
    -0.07
    etiš
    -0.07
    ìm
    -0.07
    prat
    -0.07
    POSITIVE LOGITS
    ody
    0.07
     оÑĤли
    0.07
    è¿ĶåĽŀ
    0.06
    _lazy
    0.06
    è¾°
    0.06
    ICS
    0.06
     Na
    0.06
    ixo
    0.06
    表çļĦ
    0.06
    åĪĥ
    0.06
    Activations Density 0.010%

    No Known Activations