© 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. 18660
    Prev
    Next
    INDEX
    Explanations

    x axis, ice hockey, Monash

    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
    veranst
    -0.06
    çģ¯çģ«
    -0.06
    _flag
    -0.05
    éļ¾æ±Ĥ
    -0.05
    rego
    -0.05
    incl
    -0.05
    دار
    -0.05
    erein
    -0.05
    åĬłå¯Ĩ
    -0.05
    ä¸Ĭä¸Ģç¯ĩ
    -0.05
    POSITIVE LOGITS
     kij
    0.05
    underline
    0.05
    jet
    0.05
    æĺ¯åľ¨
    0.05
    super
    0.05
    ÑģÑĮ
    0.05
    osu
    0.05
     $("<
    0.05
    yk
    0.05
    åŀĭ
    0.05
    Activations Density 0.090%

    No Known Activations