© 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. 17146
    Prev
    Next
    INDEX
    Explanations

    analyzed partial purification

    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
    rep
    -0.05
    ookie
    -0.05
     Prep
    -0.05
    è¿«
    -0.05
    åĢ¼å¾Ĺ
    -0.05
    åºĵéĩĮ
    -0.05
    jq
    -0.05
    ä¸įå¾Ĺä¸į
    -0.05
    app
    -0.05
    æĮĩåĩº
    -0.05
    POSITIVE LOGITS
    han
    0.06
    više
    0.06
    æĪijä»¬çĽ¸ä¿¡
    0.06
    rhein
    0.06
    egah
    0.06
    rano
    0.06
    åķ¡
    0.06
    entric
    0.06
     Affiliate
    0.06
    etween
    0.06
    Activations Density 0.001%

    No Known Activations