© 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. 19224
    Prev
    Next
    INDEX
    Explanations

    case labels

    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
    antal
    -0.06
    var
    -0.05
    HQ
    -0.05
    åĴĮæıIJåįĩ
    -0.05
    TargetException
    -0.05
     transm
    -0.05
    ft
    -0.05
    äºĭåĦ¿
    -0.05
    ikan
    -0.05
    ellan
    -0.05
    POSITIVE LOGITS
    èĥĮçĹĽ
    0.07
    -inverse
    0.06
     Mud
    0.06
    æ´ŀ
    0.06
    onders
    0.06
    èį«
    0.06
    éĢģä½ł
    0.06
    caler
    0.05
    éĢĨ
    0.05
    ä¾Ŀä¾Ŀ
    0.05
    Activations Density 0.002%

    No Known Activations