© 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. 22465
    Prev
    Next
    INDEX
    Explanations

    competitiveness

    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
    éral
    -0.06
    rior
    -0.06
    ornings
    -0.05
    ä¸įè¨Ģ
    -0.05
    ness
    -0.05
    ä¸Ĭéĺµ
    -0.05
    _rat
    -0.05
    adress
    -0.05
    -specific
    -0.05
    Ñħе
    -0.05
    POSITIVE LOGITS
    yaj
    0.07
    en
    0.07
    vang
    0.06
    èĩ³é«ĺ
    0.06
    rophe
    0.06
    enze
    0.06
    اÙĨ
    0.06
    encies
    0.06
    коÑģÑĤÑĮÑİ
    0.06
     lifetime
    0.05
    Activations Density 0.001%

    No Known Activations