© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16974
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
    tiges
    -0.07
    ehm
    -0.07
    éĻ¢æīĢ
    -0.07
     -:
    -0.07
    moc
    -0.06
    åħ¨ç³»åĪĹ
    -0.06
    å°±æĺ¯æĥ³
    -0.06
    erge
    -0.06
    orii
    -0.06
    yim
    -0.06
    POSITIVE LOGITS
    ation
    0.07
    /
    0.07
     ang
    0.05
    itude
    0.05
    Ø©
    0.05
    ,
    0.05
    éĢĤåºĶ
    0.05
     cent
    0.05
     suc
    0.05
    Ùħا
    0.05
    Activations Density 0.001%

    No Known Activations