© 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. 16857
    Prev
    Next
    INDEX
    Explanations

    way followed by direction

    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
    Ø©
    -0.06
    аÑģÑģив
    -0.06
     kenal
    -0.05
    arks
    -0.05
    -0.05
     jat
    -0.05
     Verl
    -0.05
    å®ĥåı¯ä»¥
    -0.05
    ÑıÑĤиÑı
    -0.05
    éĩıçļĦ
    -0.05
    POSITIVE LOGITS
    orate
    0.07
    olit
    0.07
    ÛĮØŃ
    0.06
    letz
    0.06
    rese
    0.06
    uka
    0.06
    kannya
    0.06
    rob
    0.06
    sole
    0.06
    ụ
    0.06
    Activations Density 0.007%

    No Known Activations