© 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. 20867
    Prev
    Next
    INDEX
    Explanations

    Odoo Server

    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
    éĢļ
    -0.06
    eth
    -0.05
    aub
    -0.05
     cold
    -0.05
    card
    -0.05
    主
    -0.05
     Murray
    -0.05
     Canada
    -0.05
    cold
    -0.05
    å·´åħĭ
    -0.05
    POSITIVE LOGITS
    inhos
    0.06
    ulon
    0.06
    ERO
    0.06
    ading
    0.06
    uyo
    0.06
    andone
    0.06
    صات
    0.06
    ekor
    0.06
    пли
    0.06
    uchte
    0.06
    Activations Density 0.021%

    No Known Activations