© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18615
    Prev
    Next
    INDEX
    Explanations

    bold

    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
    Resta
    -0.06
    ãĤ«æľĪ
    -0.06
    ational
    -0.06
    ciu
    -0.06
    ãģ¾ãģĽãģ¦
    -0.06
    pile
    -0.05
    å®ŀéĻħæĥħåĨµ
    -0.05
    ç«ŀ
    -0.05
    hips
    -0.05
    hlas
    -0.05
    POSITIVE LOGITS
    ed
    0.08
    stood
    0.07
    olda
    0.06
    plat
    0.06
    надо
    0.06
    uni
    0.06
    itud
    0.06
    ord
    0.06
     **:**
    0.06
    osa
    0.06
    Activations Density 0.003%

    No Known Activations