© 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. 16823
    Prev
    Next
    INDEX
    Explanations

    heat

    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
    ئ
    -0.06
    Ïĩη
    -0.06
    upt
    -0.06
    strup
    -0.06
    اء
    -0.06
    ihe
    -0.05
    iat
    -0.05
    mart
    -0.05
    دÙī
    -0.05
    rid
    -0.05
    POSITIVE LOGITS
    å¦ĸå¨Ĩ
    0.06
    æ»¡åľ°
    0.06
    æĸĩçļĦ
    0.05
     sl
    0.05
    溢
    0.05
    ebles
    0.05
    åĴĮæŶéĹ´
    0.05
    éĹ
    0.05
    besch
    0.05
    omer
    0.05
    Activations Density 0.001%

    No Known Activations