© 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. 20795
    Prev
    Next
    INDEX
    Explanations

    math problems involving sequences

    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
    åİŁåĽłåľ¨äºİ
    -0.06
    é«ĺç§ij
    -0.06
    ripp
    -0.05
    å¾ĹåIJį
    -0.05
    itti
    -0.05
     lok
    -0.05
    istine
    -0.05
    loc
    -0.05
    contra
    -0.05
    æīĢéľĢ
    -0.05
    POSITIVE LOGITS
    sic
    0.06
    çĿģ
    0.06
    秣
    0.05
    éĹ®
    0.05
    _simulation
    0.05
    žas
    0.05
     عÙĪض
    0.05
    oja
    0.05
    jes
    0.05
     randomized
    0.05
    Activations Density 0.019%

    No Known Activations