© 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. 20842
    Prev
    Next
    INDEX
    Explanations

    numpy array creation

    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
     заÑĤо
    -0.06
    ikin
    -0.06
    ocket
    -0.06
    quet
    -0.06
    Äįina
    -0.06
    rape
    -0.06
     заг
    -0.06
    AFP
    -0.05
    oot
    -0.05
    èĭŁ
    -0.05
    POSITIVE LOGITS
    æĤ¬
    0.06
     themselves
    0.05
    ster
    0.05
    andid
    0.05
    èĤĮ
    0.05
     Broadway
    0.05
    elui
    0.05
    -equiv
    0.05
    åħ¢
    0.05
    бÑĢ
    0.05
    Activations Density 0.001%

    No Known Activations