© 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. 1231
    Prev
    Next
    INDEX
    Explanations

    innovation projects

    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
    ÃľN
    -0.07
    astes
    -0.07
     relativ
    -0.07
    è§ģæѤ
    -0.07
    åѦåĬĽ
    -0.07
    ¸
    -0.07
    _SAN
    -0.07
    onga
    -0.07
    itra
    -0.07
    oração
    -0.07
    POSITIVE LOGITS
     Eden
    0.07
    umar
    0.07
    upas
    0.07
    ä¼ĺåĬ¿
    0.07
    uv
    0.06
    omen
    0.06
    r
    0.06
     _(
    0.06
    ä¹Łåıªèĥ½
    0.06
    fos
    0.06
    Activations Density 0.021%

    No Known Activations