© 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. 18159
    Prev
    Next
    INDEX
    Explanations

    transportation and driving

    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
    æĬ«
    -0.05
    èħ³
    -0.05
    触
    -0.05
     materna
    -0.05
    indir
    -0.05
     Hearts
    -0.05
    lebt
    -0.05
     circonst
    -0.05
     rencont
    -0.05
    óc
    -0.05
    POSITIVE LOGITS
     alternatives
    0.06
    axy
    0.06
    hub
    0.06
     Perk
    0.06
    çĪ½
    0.05
    hing
    0.05
    erc
    0.05
    ç»Ļ人们
    0.05
    ä¸Ģæĭ³
    0.05
    ony
    0.05
    Activations Density 0.022%

    No Known Activations