© 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. 19010
    Prev
    Next
    INDEX
    Explanations

    long-term

    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
    ëŀij
    -0.06
    guh
    -0.06
    IFS
    -0.05
     nay
    -0.05
    volu
    -0.05
    å»ī
    -0.05
    让èĩªå·±
    -0.05
    äºİ
    -0.05
    é¢Ħ
    -0.05
    ÑĥмÑĭ
    -0.05
    POSITIVE LOGITS
    es
    0.06
    fiber
    0.06
    issen
    0.06
    ÙĦاج
    0.06
    обÑĢа
    0.06
     overridden
    0.06
     vois
    0.06
    çļĦèĮĥåĽ´
    0.06
    缮æ¨Ļ
    0.05
    воÑİ
    0.05
    Activations Density 0.011%

    No Known Activations