© 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. 18640
    Prev
    Next
    INDEX
    Explanations

    other or alternatives

    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
    anha
    -0.06
     Walters
    -0.06
    åıªæĺ¯åĽłä¸º
    -0.06
    åĬłæĭ¿å¤§
    -0.06
    áºŃt
    -0.06
    alone
    -0.06
    altar
    -0.06
    æĴ¼
    -0.06
     Garner
    -0.06
    ically
    -0.06
    POSITIVE LOGITS
     Beard
    0.06
    社
    0.05
    uschen
    0.05
     Nin
    0.05
     Marino
    0.05
    ble
    0.05
    cro
    0.05
    inete
    0.05
    è¡°
    0.05
     esco
    0.05
    Activations Density 0.005%

    No Known Activations