© 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. 18017
    Prev
    Next
    INDEX
    Explanations

    written agreement or permission

    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
     Differ
    -0.05
    ella
    -0.05
    ño
    -0.05
    rekt
    -0.05
    ç§į
    -0.05
     globe
    -0.05
    eter
    -0.05
    è´Łéĩį
    -0.05
     Relig
    -0.05
    两
    -0.05
    POSITIVE LOGITS
    ties
    0.07
    idas
    0.06
    unteers
    0.06
    lege
    0.06
    ÑĤол
    0.06
    ney
    0.06
    кÑĢепи
    0.06
    leck
    0.06
    trim
    0.06
     pire
    0.06
    Activations Density 0.017%

    No Known Activations