© 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. 17864
    Prev
    Next
    INDEX
    Explanations

    hope it will be

    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
    iri
    -0.06
    iqu
    -0.06
    rie
    -0.06
    çŁ¥
    -0.06
     casc
    -0.05
    ases
    -0.05
    åĭĩ
    -0.05
    asi
    -0.05
    殿
    -0.05
    è¿Ļé¢Ĺ
    -0.05
    POSITIVE LOGITS
    askell
    0.06
    frig
    0.06
    ì²Ļ
    0.06
    artes
    0.06
    APTER
    0.06
    oucher
    0.05
    صاب
    0.05
    ackbar
    0.05
    DRV
    0.05
    æľīè¯Ŀ
    0.05
    Activations Density 0.001%

    No Known Activations