© 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. 17524
    Prev
    Next
    INDEX
    Explanations

    api data

    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
    çĵ¢
    -0.06
    )const
    -0.05
    until
    -0.05
    ughters
    -0.05
    oot
    -0.05
     Parch
    -0.05
    ère
    -0.05
    éĴ³
    -0.05
    PEC
    -0.05
    finite
    -0.05
    POSITIVE LOGITS
     takeaway
    0.06
    rosso
    0.06
    è¦ĨçĽĸéĿ¢
    0.06
     pass
    0.06
    åIJķ
    0.05
    åIJijæĹ¥
    0.05
    å¿ĥåľ°
    0.05
    ogs
    0.05
    è
    0.05
    جاÙĩ
    0.05
    Activations Density 0.009%

    No Known Activations