© 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. 20561
    Prev
    Next
    INDEX
    Explanations

    asking or making requests

    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
     Chev
    -0.07
    ysh
    -0.07
    Äįili
    -0.06
    éŁ³åĥı
    -0.06
    åĬłæĭ¿å¤§çļĦ
    -0.06
     accueill
    -0.06
     exceptionnelle
    -0.06
    éĩĮåİ»
    -0.06
    acol
    -0.06
    ooth
    -0.06
    POSITIVE LOGITS
     ku
    0.06
    rd
    0.05
     irrelevant
    0.05
     recurrent
    0.05
     successive
    0.05
    ()
    0.05
     uw
    0.05
     attempting
    0.05
     mind
    0.04
     mente
    0.04
    Activations Density 0.001%

    No Known Activations