© 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. 11253
    Prev
    Next
    INDEX
    Explanations

    diagonal matrix

    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
    ebes
    -0.08
    ARING
    -0.08
    æĿİè½»
    -0.08
    поÑĤÑĢе
    -0.07
    ehr
    -0.07
    áĢ¸
    -0.07
    ÑīеÑĤ
    -0.07
    werben
    -0.07
    aventure
    -0.07
    GENCY
    -0.07
    POSITIVE LOGITS
    ç¦ıç¦Ħ
    0.07
    -ish
    0.06
    enerate
    0.06
    ़
    0.06
    è¿Ļæĺ¯æĪijçļĦ
    0.06
    صب
    0.06
    å°Ķå¾·
    0.06
    ation
    0.06
    à¸ķัว
    0.06
    ?,?,
    0.06
    Activations Density 0.001%

    No Known Activations