© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19456
    Prev
    Next
    INDEX
    Explanations

    code structure

    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
    á»Ĺi
    -0.07
     resembl
    -0.07
    ungg
    -0.06
    iraz
    -0.06
    ä½łä»¬éĥ½
    -0.06
    ught
    -0.06
     certif
    -0.06
    scheid
    -0.06
    éo
    -0.06
    unti
    -0.06
    POSITIVE LOGITS
     many
    0.05
    adar
    0.05
     ÑĢода
    0.05
    ivic
    0.05
    lie
    0.05
    ç§ij
    0.05
     vern
    0.05
    insa
    0.05
    vend
    0.05
    æ³ķ
    0.04
    Activations Density 0.008%

    No Known Activations