© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20310
    Prev
    Next
    INDEX
    Explanations

    view content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ات
    -0.06
    ments
    -0.06
    å¤Ħ
    -0.05
    asan
    -0.05
    åĸĦ
    -0.05
    s
    -0.05
    let
    -0.05
    ademia
    -0.05
     ÑĤак
    -0.05
     path
    -0.05
    POSITIVE LOGITS
    weile
    0.07
    óx
    0.06
    гда
    0.06
    å¥½å·¥ä½ľ
    0.06
    ocking
    0.06
    archical
    0.06
     comprim
    0.06
    collapsed
    0.06
    ulli
    0.06
    cats
    0.06
    Activations Density 0.022%

    No Known Activations