© 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. 22487
    Prev
    Next
    INDEX
    Explanations

    time passing or progression

    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
    Negative Logits
    иÑģÑĤ
    -0.06
    за
    -0.05
    åĩı
    -0.05
     بار
    -0.05
    less
    -0.05
    freeze
    -0.05
    roman
    -0.05
    erat
    -0.05
    ionen
    -0.05
    å®īåħ¨
    -0.04
    POSITIVE LOGITS
    линд
    0.07
    tif
    0.07
    nal
    0.07
    arine
    0.07
    ابÛĮ
    0.07
    ti
    0.07
    czeÅĽ
    0.07
    emoc
    0.07
    ÙĦع
    0.06
    :block
    0.06
    Activations Density 0.001%

    No Known Activations