© 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. 17315
    Prev
    Next
    INDEX
    Explanations

    software and applications

    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
    s
    -0.06
    -0.05
     sprink
    -0.05
    e
    -0.05
     guard
    -0.05
     -
    -0.05
     deployments
    -0.05
    å¤ĸè¡£
    -0.05
    å®ī
    -0.05
     co
    -0.05
    POSITIVE LOGITS
     véh
    0.07
    astia
    0.07
     deltaTime
    0.07
     photoshop
    0.07
    åĽłæĿIJ
    0.07
    æŃ£çīĪ
    0.07
    åľ¨æľ¬ç«Ļ
    0.07
    angsa
    0.07
    éĽĦåİļ
    0.06
    解åİĭ
    0.06
    Activations Density 0.024%

    No Known Activations