© 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. 21302
    Prev
    Next
    INDEX
    Explanations

    last followed by time/sequence indicator

    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
    ément
    -0.08
    áŁĩ
    -0.08
    zyst
    -0.08
    andes
    -0.08
    italia
    -0.08
    oyo
    -0.08
    ibas
    -0.08
    ãĥ¼ãĤ¿
    -0.08
    peg
    -0.08
     Lassen
    -0.08
    POSITIVE LOGITS
    åħ³å¤´
    0.10
    -ever
    0.10
    ly
    0.10
    ness
    0.09
    -minute
    0.09
    OrDefault
    0.09
    rophe
    0.08
    itude
    0.08
    most
    0.08
    åĴĮåīį
    0.08
    Activations Density 0.053%

    No Known Activations