© 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. 21175
    Prev
    Next
    INDEX
    Explanations

    stunts and tricks

    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
    tern
    -0.05
    éĢĤ
    -0.05
    ä¸įåı¯å¿½è§Ĩ
    -0.05
    иден
    -0.05
     sensible
    -0.05
    è®¤çľŁ
    -0.05
     Highlands
    -0.05
    éļıé£İ
    -0.05
    éĢĤä¸Ń
    -0.05
    /generated
    -0.05
    POSITIVE LOGITS
     Diri
    0.08
    éĭª
    0.07
    ıs
    0.06
    ople
    0.06
     pave
    0.06
     doble
    0.06
     paving
    0.06
    bord
    0.06
    éĵºåŀ«
    0.06
    解éļ¾
    0.06
    Activations Density 0.008%

    No Known Activations