© 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. 21767
    Prev
    Next
    INDEX
    Explanations

    accurate

    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
    ÐłÐŀÐĴ
    -0.06
    äksi
    -0.06
    olina
    -0.06
    chez
    -0.05
    hak
    -0.05
    .lon
    -0.05
    bed
    -0.05
    Amb
    -0.05
     cinematic
    -0.05
     amb
    -0.05
    POSITIVE LOGITS
    utral
    0.06
    aug
    0.06
    ваÑĢ
    0.06
     informat
    0.05
    è¨Ĺ
    0.05
     Provinc
    0.05
    wares
    0.05
    годаÑĢ
    0.05
    å¡ŀå°Ķ
    0.05
    è¿ĩ好
    0.05
    Activations Density 0.004%

    No Known Activations