© 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. 17043
    Prev
    Next
    INDEX
    Explanations

    angiography and interventions

    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
    uban
    -0.06
    elih
    -0.06
     пÑĢиб
    -0.06
     Rum
    -0.06
     bok
    -0.06
    åºĶèĢĥèĻij
    -0.06
    ekl
    -0.06
    posts
    -0.06
    anit
    -0.06
    pec
    -0.05
    POSITIVE LOGITS
    æݢ索
    0.05
     roaming
    0.05
     exploration
    0.05
    åıijçİ°
    0.05
     corrett
    0.05
    åijµ
    0.05
     discover
    0.05
    spl
    0.05
     names
    0.05
     junk
    0.05
    Activations Density 0.183%

    No Known Activations