© 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. 16845
    Prev
    Next
    INDEX
    Explanations

    remove / out

    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
    æ¶ħ
    -0.07
    æ¯ıåĪĨéĴŁ
    -0.06
    æĻºèĥ½
    -0.06
    çĤ³
    -0.06
    éĶĢ
    -0.05
    мÑı
    -0.05
     intelligent
    -0.05
    åĪĨæŶ
    -0.05
    å¼¥
    -0.05
    ensor
    -0.05
    POSITIVE LOGITS
    cache
    0.06
    /cache
    0.06
    cati
    0.06
     spoilers
    0.06
    ÙĬÙħØ©
    0.06
    ìłķìĿĺ
    0.06
    ิ
    0.06
     سÙĪØ¡
    0.06
    ç¿»æĸ°
    0.06
    å°ı鼨
    0.06
    Activations Density 0.020%

    No Known Activations