© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17492
    Prev
    Next
    INDEX
    Explanations

    install/fitting

    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
    -step
    -0.06
     pathway
    -0.06
    lyph
    -0.06
    yo
    -0.06
    .GenerationType
    -0.06
    ɵ
    -0.06
    /sources
    -0.05
    otp
    -0.05
     sosten
    -0.05
    ض
    -0.05
    POSITIVE LOGITS
     turnovers
    0.06
    ä¸īåĪĨ
    0.06
     Handle
    0.06
    å®ī
    0.06
    cata
    0.06
    å®ı
    0.05
    深水
    0.05
    åįļæĸĩ
    0.05
    å½ķåĥı
    0.05
    برة
    0.05
    Activations Density 0.027%

    No Known Activations