© 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. 19066
    Prev
    Next
    INDEX
    Explanations

    huge, very, big, significant, important, lot

    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
    ingly
    -0.06
    æĢ§éĹ®é¢ĺ
    -0.06
     almost
    -0.06
    lick
    -0.05
    onal
    -0.05
    åĩłä¹İæīĢæľī
    -0.05
    lica
    -0.05
    说äºĨ
    -0.05
    roe
    -0.05
     hard
    -0.05
    POSITIVE LOGITS
    itom
    0.06
    aven
    0.06
     satisf
    0.06
    biz
    0.06
    ologista
    0.06
    fum
    0.06
    знÑı
    0.06
    variant
    0.06
    ifest
    0.06
    ettor
    0.06
    Activations Density 0.111%

    No Known Activations