© 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. 20652
    Prev
    Next
    INDEX
    Explanations

    vector magnitude $

    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
    akin
    -0.06
    bers
    -0.06
    iak
    -0.06
    å§Ĩæĸ¯
    -0.06
    neb
    -0.06
    programma
    -0.06
    жнее
    -0.06
    ánd
    -0.06
    зок
    -0.06
     Ever
    -0.06
    POSITIVE LOGITS
    antu
    0.05
    å°º
    0.05
    ÑĺÑĥ
    0.05
    æģ¯
    0.05
    åįĩ
    0.05
    emi
    0.05
    个æĪĸå¤ļ个
    0.05
     expectations
    0.05
    举æīĭ
    0.05
    CR
    0.05
    Activations Density 0.015%

    No Known Activations