© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18368
    Prev
    Next
    INDEX
    Explanations

    4

    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
    æĶĺ
    -0.06
    èĶ·
    -0.05
    wirtschaft
    -0.05
     share
    -0.05
     trif
    -0.05
    elah
    -0.05
    ruf
    -0.05
     Power
    -0.05
     power
    -0.05
     Foot
    -0.05
    POSITIVE LOGITS
    aknya
    0.06
    ohner
    0.06
    æ·±åľ³å¸Ĥå®Ŀå®īåĮº
    0.06
    atitude
    0.06
    üglich
    0.06
    arged
    0.06
    saus
    0.06
    schluss
    0.06
     رسÙħÛĮ
    0.06
    .JpaRepository
    0.06
    Activations Density 0.056%

    No Known Activations