© 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. 20150
    Prev
    Next
    INDEX
    Explanations

    function or method calls

    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
    ware
    -0.06
     indu
    -0.05
    çĢ¬
    -0.05
    best
    -0.05
    иÑģк
    -0.05
    agn
    -0.05
    好çİ©
    -0.05
    enton
    -0.05
     best
    -0.05
    Follow
    -0.05
    POSITIVE LOGITS
     alone
    0.07
    ttet
    0.06
    zam
    0.06
    klusive
    0.06
    ีà¹Ī
    0.06
    rack
    0.06
    ãģŁãģı
    0.06
    ingleton
    0.06
     müs
    0.05
    orges
    0.05
    Activations Density 0.095%

    No Known Activations