© 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. 17007
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    oare
    -0.07
    è¿ĩ
    -0.06
    æķħå±ħ
    -0.06
    arqu
    -0.06
    óst
    -0.06
    é©ļåĸľ
    -0.06
    ä¸ī代
    -0.06
    icÃŃ
    -0.05
    Åijbb
    -0.05
     bumped
    -0.05
    POSITIVE LOGITS
     length
    0.07
    ç¯ĩå¹ħ
    0.06
     Length
    0.06
    errupt
    0.06
    (sizeof
    0.06
    éķ¿åº¦ä¸º
    0.06
     dÃłi
    0.06
    length
    0.06
    éķ¿è¾¾
    0.06
    åħ±
    0.05
    Activations Density 0.187%

    No Known Activations