© 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. 20987
    Prev
    Next
    INDEX
    Explanations

    add specific items

    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
    chetti
    -0.10
    Ø©
    -0.09
    ãģĺãĤģ
    -0.08
    वल
    -0.08
     اÙĦØŃاÙĦ
    -0.08
    à¯įà®ķ
    -0.08
    iramente
    -0.08
    icke
    -0.08
    ï¸İ
    -0.08
    oples
    -0.08
    POSITIVE LOGITS
    ITIONAL
    0.13
    OrUpdate
    0.13
    ition
    0.12
    /remove
    0.12
    uctor
    0.11
    uct
    0.11
    /rem
    0.11
    -ons
    0.10
    itive
    0.10
    itionally
    0.10
    Activations Density 0.078%

    No Known Activations