© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19166
    Prev
    Next
    INDEX
    Explanations

    Amanda Bynes

    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
    irikan
    -0.06
    æĶ¿æ³ķå§Ķ
    -0.06
    æ¦Ľ
    -0.05
    boh
    -0.05
    æĮĩå®ļ
    -0.05
    oton
    -0.05
    åįĥ人
    -0.05
     "')
    -0.05
    sein
    -0.05
    athing
    -0.05
    POSITIVE LOGITS
    ža
    0.06
    åħ¼
    0.06
    xico
    0.05
    ;&
    0.05
    ent
    0.05
     Aga
    0.05
    endant
    0.05
    箫
    0.05
    åIJĮæŶè¦ģ
    0.05
    icient
    0.05
    Activations Density 0.001%

    No Known Activations