© 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. 20970
    Prev
    Next
    INDEX
    Explanations

    questions and statements

    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
     otherwise
    -0.05
     sint
    -0.05
    amen
    -0.05
    è¿ĶåĽŀ顶éĥ¨
    -0.05
    æľīæĿĥ
    -0.05
    ikli
    -0.05
     limp
    -0.05
    Anyway
    -0.05
     leve
    -0.05
    isten
    -0.05
    POSITIVE LOGITS
    åħ¶ä¸ī
    0.07
    (mappedBy
    0.06
    ÑĤÑİ
    0.06
    ä½Ļç¯ĩ
    0.06
    εδ
    0.06
    太éĥİ
    0.06
    åħ·åIJĪ
    0.06
    å¹´çļĦåıijå±ķ
    0.06
    aiss
    0.06
    iencia
    0.06
    Activations Density 0.012%

    No Known Activations