© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22315
    Prev
    Next
    INDEX
    Explanations

    duration of"}, "Duration: "}

    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
    ech
    -0.06
    ore
    -0.06
    tid
    -0.05
    读åį¡
    -0.05
    arger
    -0.05
     Ple
    -0.05
    igrated
    -0.05
    ert
    -0.05
    -
    -0.04
    ached
    -0.04
    POSITIVE LOGITS
    wards
    0.09
    ä¸įéĶĻäºĨ
    0.08
    nable
    0.07
    кÑĢепи
    0.07
    lus
    0.07
    ané
    0.07
    é¹ĥ
    0.07
    ا
    0.07
    acious
    0.07
    ÑĪком
    0.07
    Activations Density 0.010%

    No Known Activations