© 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. 21681
    Prev
    Next
    INDEX
    Explanations

    over

    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
    roid
    -0.06
    weep
    -0.06
    orse
    -0.06
    ors
    -0.06
    oczyn
    -0.06
    existent
    -0.06
    æĥ¨
    -0.06
    öra
    -0.06
    uds
    -0.06
    rix
    -0.06
    POSITIVE LOGITS
    epend
    0.06
    ä¸į失
    0.05
    azing
    0.05
     Opin
    0.05
    BR
    0.05
     Br
    0.05
    .UtcNow
    0.05
     beho
    0.05
    éĽĨåIJĪ
    0.05
    æŀķ
    0.05
    Activations Density 0.006%

    No Known Activations