© 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. 22515
    Prev
    Next
    INDEX
    Explanations

    mathematical equations defining parameters

    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
    å·¥ä½ľæĺ¯
    -0.06
     acost
    -0.06
    elts
    -0.06
    moil
    -0.06
    ç»ĥ
    -0.06
    ecz
    -0.06
     trac
    -0.06
    anz
    -0.06
    ãģ¤ãĤĤãĤĬ
    -0.06
    PLICATION
    -0.06
    POSITIVE LOGITS
    hin
    0.07
     idé
    0.06
    oriously
    0.05
    ly
    0.05
    ä½Ĩä¸įéĻIJäºİ
    0.05
    en
    0.05
    èĩ³å°ij
    0.05
    asuk
    0.05
     elemental
    0.05
    èµ·çłģ
    0.05
    Activations Density 0.019%

    No Known Activations