© 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. 16880
    Prev
    Next
    INDEX
    Explanations

    programming language constructs

    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
    bli
    -0.06
    ples
    -0.06
     Location
    -0.06
    gel
    -0.06
    alu
    -0.06
    ialect
    -0.06
    æĹŃ
    -0.06
    ее
    -0.06
     Ori
    -0.06
    bles
    -0.06
    POSITIVE LOGITS
    .mk
    0.06
    á»ĵng
    0.05
    主
    0.05
    endl
    0.05
    ago
    0.05
    on
    0.05
     major
    0.05
    town
    0.05
    .flatMap
    0.05
    天åij½
    0.05
    Activations Density 0.005%

    No Known Activations