© 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. 22104
    Prev
    Next
    INDEX
    Explanations

    cross examines

    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
    纱
    -0.06
    社
    -0.06
    çŃ
    -0.05
    è°ģ
    -0.05
    ç¾Ĭ
    -0.05
    çĶ±æѤ
    -0.05
    çĽ¸ä¼¼
    -0.05
    äºĭå¾Į
    -0.05
    .extensions
    -0.05
    sc
    -0.05
    POSITIVE LOGITS
    riot
    0.06
    ек
    0.06
    RIOS
    0.06
    fér
    0.06
    转移åĪ°
    0.06
    udid
    0.06
    afe
    0.06
    æ±Ĥç²¾
    0.06
    pak
    0.06
    ç«ŀäºī对æīĭ
    0.06
    Activations Density 0.148%

    No Known Activations