© 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. 60962
    Prev
    Next
    INDEX
    Explanations

    per unit/entity

    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
    udian
    -0.08
    inson
    -0.08
    ä¸ĩéĩĮ
    -0.07
    _EXTRA
    -0.07
    eny
    -0.07
    iere
    -0.07
    ToPoint
    -0.07
    rej
    -0.07
    yne
    -0.07
    baran
    -0.07
    POSITIVE LOGITS
     annum
    0.08
     tùy
    0.06
    ìĶ©
    0.06
    åĿİ
    0.06
    ùm
    0.06
     má»Ĺi
    0.06
    áºŃm
    0.06
    змо
    0.06
     depending
    0.06
    å¤ĸåĬł
    0.06
    Activations Density 0.076%

    No Known Activations