© 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. 22552
    Prev
    Next
    INDEX
    Explanations

    programming results and output

    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
    rier
    -0.06
    ži
    -0.06
    ãĤĦãĤĬ
    -0.05
     pergun
    -0.05
    åij¨å²ģ以ä¸ĭ
    -0.05
    antin
    -0.05
    uoj
    -0.05
    porteur
    -0.05
    èī¯
    -0.05
     relatively
    -0.05
    POSITIVE LOGITS
    obr
    0.06
    itas
    0.06
    &id
    0.05
    urat
    0.05
    idis
    0.05
    ÏĥοÏħ
    0.05
    åħ¶èĩªçĦ¶
    0.05
    好象
    0.05
     UR
    0.05
    usch
    0.05
    Activations Density 0.019%

    No Known Activations