© 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. 17709
    Prev
    Next
    INDEX
    Explanations

    intellectual property or decline

    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
    /loading
    -0.07
    hias
    -0.07
    adier
    -0.07
     protes
    -0.07
    ear
    -0.07
    ahoo
    -0.06
    schlieÃŁlich
    -0.06
    gst
    -0.06
    Slash
    -0.06
     عج
    -0.06
    POSITIVE LOGITS
    ¡
    0.06
    ware
    0.05
    scht
    0.05
    mate
    0.05
    راء
    0.05
     vice
    0.05
    веÑĤ
    0.05
    å¥Ķ
    0.05
    æī³
    0.05
    å°Ķ
    0.05
    Activations Density 0.003%

    No Known Activations