© 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. 21906
    Prev
    Next
    INDEX
    Explanations

    relative position or value

    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
    è®Ń
    -0.07
    ç»ĩ
    -0.06
    è¨ĵ
    -0.06
    游
    -0.06
    åıĸäºĨ
    -0.06
    ockets
    -0.06
    ве
    -0.05
    ovol
    -0.05
    èªĬ
    -0.05
    isans
    -0.05
    POSITIVE LOGITS
     far
    0.06
     last
    0.06
    ä¸ĢéĢļ
    0.06
    Į¨
    0.05
    last
    0.05
     reverse
    0.05
     flux
    0.05
    far
    0.05
     lead
    0.05
     special
    0.05
    Activations Density 0.062%

    No Known Activations