© 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. 22051
    Prev
    Next
    INDEX
    Explanations

    mathematical limits and continuity

    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
    vang
    -0.06
    ogan
    -0.06
    erial
    -0.05
    b
    -0.05
    çĶŁåĩº
    -0.05
    ³
    -0.05
    äºĴè¡¥
    -0.05
    cident
    -0.05
    ardu
    -0.05
    lap
    -0.05
    POSITIVE LOGITS
    éĢ¼è¿ij
    0.07
    éľ
    0.06
     arred
    0.06
    æ±Ģ
    0.06
     convergence
    0.06
     gas
    0.06
    åĩĿ
    0.06
    izador
    0.06
    Gran
    0.06
    unst
    0.06
    Activations Density 0.053%

    No Known Activations