© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 32319
    Prev
    Next
    INDEX
    Explanations

    grievance, complaints, peeves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    ä»Ģä¹Īæł·
    -0.09
    åłĩ
    -0.09
    è¿ĩ硬
    -0.08
    èĬĤèĥ½
    -0.08
    аÑĢам
    -0.08
    ibrary
    -0.08
    anner
    -0.08
    纪å§Ķ
    -0.08
    .GetInstance
    -0.08
    ug
    -0.08
    POSITIVE LOGITS
    mlin
    0.10
    opot
    0.10
    oire
    0.10
    /question
    0.10
    è¡·
    0.09
    atif
    0.09
    atten
    0.09
    æ¸ł
    0.09
    -minded
    0.09
    鸡汤
    0.09
    Activations Density 0.005%

    No Known Activations