© 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. 17961
    Prev
    Next
    INDEX
    Explanations

    file paths and usernames

    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
    åŁŁ
    -0.06
    erei
    -0.06
    fach
    -0.06
    åľĴ
    -0.06
    åŁŁçļĦ
    -0.06
    iqu
    -0.06
    arz
    -0.06
    igr
    -0.05
    imes
    -0.05
    öse
    -0.05
    POSITIVE LOGITS
    åĪĨå¸ĥå¦Ĥä¸ĭ
    0.06
    å°ĺåŁĥ
    0.05
    è¿Ļå°±
    0.05
    shal
    0.05
    stitu
    0.05
     inse
    0.05
     lu
    0.05
     пÑĭлÑĮ
    0.05
     Gust
    0.05
    éĺµé£İ
    0.05
    Activations Density 0.040%

    No Known Activations