© 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. 58055
    Prev
    Next
    INDEX
    Explanations

    why questions

    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
    alow
    -0.08
    taggio
    -0.07
    uerta
    -0.07
    utte
    -0.07
    иÑĤеÑĤа
    -0.07
    awang
    -0.07
    EGIN
    -0.07
    .ONE
    -0.07
    rowsing
    -0.07
     Entries
    -0.07
    POSITIVE LOGITS
    /how
    0.08
    以åıĬå¦Ĥä½ķ
    0.08
    erso
    0.07
    ä½ķåľ°
    0.07
    akit
    0.06
     questions
    0.06
    questions
    0.06
    osto
    0.06
    ÄŁ
    0.06
    ذا
    0.06
    Activations Density 0.081%

    No Known Activations