© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22396
    Prev
    Next
    INDEX
    Explanations

    gradient flow

    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
    Negative Logits
    ness
    -0.08
    ellaneous
    -0.06
    åĽŀäºĭ
    -0.06
    gie
    -0.06
    go
    -0.06
    iveness
    -0.06
    itecture
    -0.06
    ption
    -0.06
    gu
    -0.06
    gan
    -0.05
    POSITIVE LOGITS
    thal
    0.07
     **^
    0.06
    à¹ģรà¸ĩ
    0.06
    enj
    0.06
    åħļæĹĹ
    0.06
    ÑģÑĤеÑģÑĤвенно
    0.06
    thren
    0.06
    ONGL
    0.06
    çĥŃéŨæĸĩç«ł
    0.06
    vere
    0.06
    Activations Density 0.005%

    No Known Activations