© 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. 18958
    Prev
    Next
    INDEX
    Explanations

    reset commands and actions

    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
    ran
    -0.05
     Wend
    -0.05
     om
    -0.05
    ré
    -0.05
     awkward
    -0.05
    enn
    -0.05
    mx
    -0.05
    eco
    -0.05
     undert
    -0.04
    å©ķ
    -0.04
    POSITIVE LOGITS
    anam
    0.07
    ä¿Ĺ
    0.06
     couver
    0.06
    schul
    0.06
    upu
    0.06
    endance
    0.06
    onton
    0.06
    æ°¸å®ī
    0.06
    anne
    0.06
    çĥŃéŨæݨèįIJ
    0.06
    Activations Density 0.003%

    No Known Activations