© 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. 22066
    Prev
    Next
    INDEX
    Explanations

    connection strings and pooling

    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
    afs
    -0.06
     gib
    -0.06
    ç´į
    -0.06
    ÑĦÑĢи
    -0.05
    å¸IJ
    -0.05
    szy
    -0.05
     dạ
    -0.05
    纳
    -0.05
     sor
    -0.05
    rost
    -0.05
    POSITIVE LOGITS
    触åĬ¨
    0.06
    anium
    0.06
    çĻ¼è¡Į
    0.05
     jed
    0.05
    è¯ķè¯ķ
    0.05
    elier
    0.05
    åıijè¡Į
    0.05
    à¸Ļึà¸ĩ
    0.05
     dreaming
    0.05
     hand
    0.05
    Activations Density 0.007%

    No Known Activations