© 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
    2. Qwen3.5-4B
    3. 15-RES-MATRYOSHKA-65K
    4. 21100
    Prev
    Next
    INDEX
    Explanations

    special character delimiters

    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
    x
    -0.06
    ...\
    -0.06
    ...).
    -0.06
    个æ¡Ī
    -0.05
    â̦and
    -0.05
    ...*
    -0.05
    elles
    -0.05
    â̦).
    -0.05
    ...,
    -0.05
    .u
    -0.05
    POSITIVE LOGITS
    yll
    0.06
    åĪĩåħ¥çĤ¹
    0.06
    æķ´ä¸ªéĹ®é¢ĺ
    0.06
    æĶ¯æĮģåĬĽåº¦
    0.06
    ований
    0.06
    дений
    0.06
     Naturalmente
    0.06
    auff
    0.06
    Assignable
    0.06
     Shack
    0.06
    Activations Density 0.019%

    No Known Activations