© 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. 17729
    Prev
    Next
    INDEX
    Explanations

    a special word

    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
    oi
    -0.05
    ä¿¡
    -0.05
    -theme
    -0.05
    ä¾Ī
    -0.05
    apy
    -0.05
    ebel
    -0.05
     pens
    -0.05
    oire
    -0.05
    奢
    -0.05
    èĪįä¸įå¾Ĺ
    -0.05
    POSITIVE LOGITS
    çŁ¥éģĵèĩªå·±çļĦ
    0.06
    iver
    0.06
     méc
    0.06
    å·¨èµĦ
    0.06
    ickl
    0.06
    Ñģен
    0.06
    imary
    0.06
    acea
    0.06
    ä½łä»¬çļĦ
    0.06
    为己任
    0.06
    Activations Density 0.037%

    No Known Activations