© 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. 16896
    Prev
    Next
    INDEX
    Explanations

    links to watch

    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
    reeze
    -0.06
    -stack
    -0.06
    大é£İ
    -0.06
    lega
    -0.06
    ÏĪη
    -0.06
     Ùħرات
    -0.05
    redo
    -0.05
    çļĦ设计é£İæł¼
    -0.05
    /GPL
    -0.05
    stack
    -0.05
    POSITIVE LOGITS
    ives
    0.06
    ursor
    0.05
    ena
    0.05
    ordin
    0.05
    ipient
    0.05
     inst
    0.05
    å¾Īå¤ļéĹ®é¢ĺ
    0.05
    iv
    0.05
    antes
    0.05
    ÏĮν
    0.05
    Activations Density 0.018%

    No Known Activations