© 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. 16897
    Prev
    Next
    INDEX
    Explanations

    random seed or instantiation

    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
    Verk
    -0.06
    reserved
    -0.06
    Reserved
    -0.06
    èIJ±
    -0.05
    arca
    -0.05
    าว
    -0.05
     pneumat
    -0.05
    å¹³åĿĩåĪĨ
    -0.05
    .amazon
    -0.05
    haft
    -0.05
    POSITIVE LOGITS
    èµĸ
    0.06
    è³´
    0.06
    NIS
    0.06
    nis
    0.06
    (seed
    0.05
    ÑģÑĤеÑģÑĤвенно
    0.05
    iqu
    0.05
     Sources
    0.05
    vari
    0.05
    urable
    0.05
    Activations Density 0.004%

    No Known Activations