© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9712
    Prev
    Next
    INDEX
    Explanations

    task of

    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
    gere
    -0.11
    çIJĨ念
    -0.10
    åīįæıIJæĺ¯
    -0.10
    ilda
    -0.09
    çĶŁäº§èĥ½åĬĽ
    -0.09
    设计çIJĨ念
    -0.09
    CM
    -0.08
    _nr
    -0.08
    åīįæıIJ
    -0.08
    ä¸įäºĨ
    -0.08
    POSITIVE LOGITS
    èī°å·¨
    0.18
    çļĦä»»åĬ¡
    0.13
    ä»»åĬ¡
    0.13
     task
    0.13
    ä»»åĭĻ
    0.12
    task
    0.12
     tarea
    0.12
     ÑģÑĤанд
    0.12
    .Task
    0.11
     tasks
    0.11
    Activations Density 0.053%

    No Known Activations