© 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. 21323
    Prev
    Next
    INDEX
    Explanations

    unprotected, bare, alone

    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
     scorsi
    -0.06
     traditional
    -0.05
     conventional
    -0.05
    onse
    -0.05
    .setProperty
    -0.05
    åįĬ
    -0.05
    zni
    -0.05
    æľīæį®
    -0.05
     slowly
    -0.05
    轨
    -0.05
    POSITIVE LOGITS
    ross
    0.06
    raw
    0.06
    Sensitive
    0.06
    bare
    0.06
     bare
    0.05
    issan
    0.05
    ged
    0.05
     unprotected
    0.05
     sensibil
    0.05
    eltas
    0.05
    Activations Density 0.153%

    No Known Activations