© 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. 63436
    Prev
    Next
    INDEX
    Explanations

    numeric values followed by dB

    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
    bj
    -0.07
     minor
    -0.06
     Minor
    -0.06
    usc
    -0.06
    Minor
    -0.06
    çİ
    -0.06
    amo
    -0.06
    ventura
    -0.06
    rb
    -0.06
    èĬĤèĬĤ
    -0.06
    POSITIVE LOGITS
    zii
    0.08
    åħĭåĬĽ
    0.08
    aczy
    0.08
    .ua
    0.08
    .codec
    0.08
    ìŀ
    0.08
    æľĿæ°Ķ
    0.07
    nota
    0.07
    atii
    0.07
    _processors
    0.07
    Activations Density 0.053%

    No Known Activations