© 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. 19821
    Prev
    Next
    INDEX
    Explanations

    freelancer professions

    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
     either
    -0.05
    !/
    -0.05
    åİ»éĻ¤
    -0.05
    Bottom
    -0.05
     excluding
    -0.05
    bottom
    -0.05
    cntl
    -0.05
     additional
    -0.05
    åºķéĥ¨
    -0.05
    æĬľãģį
    -0.05
    POSITIVE LOGITS
    vam
    0.06
    unic
    0.06
    ashboard
    0.06
    agod
    0.06
    åħ«æĸ¹
    0.06
    éĴ§
    0.06
     batching
    0.06
     liet
    0.06
    anco
    0.06
    ureau
    0.05
    Activations Density 0.006%

    No Known Activations