© 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. 16789
    Prev
    Next
    INDEX
    Explanations

    don't be / do not be

    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
    èµ°è¿Ľ
    -0.06
    ancier
    -0.05
    ancock
    -0.05
    oarece
    -0.05
    duk
    -0.05
    ductive
    -0.05
    ddy
    -0.05
    ze
    -0.05
     unpl
    -0.05
    ลà¸ĩà¹Ħà¸Ľ
    -0.05
    POSITIVE LOGITS
    ä¸Ģ度
    0.06
    ÄįÃŃ
    0.06
    åľŃ
    0.06
    alin
    0.06
    ali
    0.06
    çĶļ
    0.06
    attempt
    0.06
    lin
    0.05
    Ĥ¬
    0.05
    ales
    0.05
    Activations Density 0.002%

    No Known Activations