© 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. 20713
    Prev
    Next
    INDEX
    Explanations

    new TypeError

    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
    koh
    -0.06
    om
    -0.06
    industr
    -0.06
     Firstly
    -0.06
    enske
    -0.06
    <g
    -0.06
    ãģĨãģ¡ãģ«
    -0.06
    åıĪæĺ¯ä¸Ģ
    -0.06
    çĵ
    -0.05
    веÑĢÑĪенÑģÑĤво
    -0.05
    POSITIVE LOGITS
    çIJĨ
    0.05
    (crate
    0.05
     wzglÄĻd
    0.05
    rap
    0.05
    İ
    0.05
    çIJĨåĮĸ
    0.05
    erable
    0.05
     ëĤ
    0.05
    ÙĦا
    0.05
    ç®±
    0.05
    Activations Density 0.015%

    No Known Activations