© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18594
    Prev
    Next
    INDEX
    Explanations

    the following

    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
     herself
    -0.06
    hir
    -0.06
    him
    -0.06
     yourself
    -0.06
    åħ·
    -0.06
    çļĦåŃĺåľ¨
    -0.06
     Yourself
    -0.05
    æľ¬äºº
    -0.05
    èĥ½è®©ä½ł
    -0.05
    па
    -0.05
    POSITIVE LOGITS
    ória
    0.06
    èį£åħī
    0.06
    åı¯æĢľçļĦ
    0.05
    èĭ±éĽĦçļĦ
    0.05
     kiếp
    0.05
    »)
    0.05
    çĹīæĮĽ
    0.05
    æĥ¨åı«
    0.05
    ালà§ĩর
    0.05
    åªĴä½ĵçļĦ
    0.05
    Activations Density 0.001%

    No Known Activations