© 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. 17385
    Prev
    Next
    INDEX
    Explanations

    text input fields

    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
    arco
    -0.06
     ours
    -0.05
    chio
    -0.05
    nero
    -0.05
    enne
    -0.05
     kompat
    -0.05
    ä¸Ģè§Ĵ
    -0.05
    è»Ĵ
    -0.05
    ears
    -0.05
    æĺ¯åĵªä¸ª
    -0.05
    POSITIVE LOGITS
    æ¸Ī
    0.06
    缩
    0.06
     contents
    0.06
     Sav
    0.05
    odin
    0.05
    uely
    0.05
     sav
    0.05
    ×ķ×¢
    0.05
    åı¯ä¹IJ
    0.05
    æĽ´çĶŁ
    0.05
    Activations Density 0.003%

    No Known Activations