© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30016
    Prev
    Next
    INDEX
    Explanations

    ADVERTISEMENT or SHARE

    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
    otte
    -0.08
     sake
    -0.06
    swer
    -0.06
    bj
    -0.06
    oth
    -0.06
    éĿ¢é£Ł
    -0.06
     prime
    -0.06
    ansa
    -0.06
    bn
    -0.06
    holm
    -0.06
    POSITIVE LOGITS
    _Static
    0.08
    (static
    0.08
    /static
    0.08
    irro
    0.08
    irma
    0.08
    dzie
    0.08
    еÑģÑģи
    0.07
    BufferSize
    0.07
    umes
    0.07
    iramente
    0.07
    Activations Density 0.005%

    No Known Activations