© 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. 18721
    Prev
    Next
    INDEX
    Explanations

    certificate request

    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
    еÑĪ
    -0.06
     Som
    -0.05
     gar
    -0.05
    erk
    -0.05
    XX
    -0.05
    åİŁçIJĨ
    -0.05
    acs
    -0.05
    ®
    -0.05
     acc
    -0.05
    omi
    -0.05
    POSITIVE LOGITS
    asten
    0.07
    orgen
    0.06
    èĮģ
    0.06
    大åĮħ
    0.06
     hadn
    0.06
    بÙĪر
    0.06
     vorstellen
    0.06
    ä¸ĭæĮ«
    0.06
    ijnen
    0.06
     affron
    0.05
    Activations Density 0.087%

    No Known Activations