© 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. 22083
    Prev
    Next
    INDEX
    Explanations

    Dim As Integer

    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
    meÄiju
    -0.06
     jeito
    -0.06
    hots
    -0.06
    اÙĦÙĬ
    -0.06
    atable
    -0.06
    ä½Ĩä¸įéĻIJäºİ
    -0.06
     пиÑģÑĮмен
    -0.06
    ALLY
    -0.06
    ICLE
    -0.06
    Ñĥж
    -0.06
    POSITIVE LOGITS
    utton
    0.06
    ãģĵãģĿ
    0.06
    eking
    0.06
    ersp
    0.05
    fe
    0.05
     lé
    0.05
     rendez
    0.05
    a
    0.05
    aux
    0.05
    inni
    0.05
    Activations Density 0.003%

    No Known Activations