© 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. 22484
    Prev
    Next
    INDEX
    Explanations

    bound to lose

    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
    urer
    -0.06
    aft
    -0.06
    çĶŁåij½çº¿
    -0.06
    TTTT
    -0.06
    eyer
    -0.06
     liger
    -0.06
    epe
    -0.06
     sustitu
    -0.06
    ©
    -0.05
    heimer
    -0.05
    POSITIVE LOGITS
     cant
    0.06
    ents
    0.05
     st
    0.05
     Cant
    0.05
     «
    0.05
    гÑĢ
    0.05
    åĴĭ
    0.05
    uche
    0.05
    .shtml
    0.05
    æľī害
    0.05
    Activations Density 0.007%

    No Known Activations