© 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. 21976
    Prev
    Next
    INDEX
    Explanations

    setContentView(R

    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
     nhiêu
    -0.06
    sted
    -0.06
    ting
    -0.06
    Ä±ÅŁ
    -0.06
    æĪijèĩªå·±çļĦ
    -0.06
    สำ
    -0.06
    ipop
    -0.05
    íݸ
    -0.05
    ter
    -0.05
    iest
    -0.05
    POSITIVE LOGITS
    s
    0.08
    scape
    0.06
    elo
    0.06
    brauch
    0.06
    urnal
    0.06
    ye
    0.06
    ño
    0.06
    Öģ
    0.06
    轩
    0.05
    elen
    0.05
    Activations Density 0.001%

    No Known Activations