© 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. 52382
    Prev
    Next
    INDEX
    Explanations

    take advantage 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
    欢è¿İæĤ¨
    -0.11
    æıIJæĭĶ
    -0.10
    hea
    -0.09
    åģļçļĦäºĭæĥħ
    -0.09
    好è¯Ħ
    -0.08
    å¤ļåľ°
    -0.08
    åĢ¡
    -0.08
    çĭł
    -0.08
    iveness
    -0.08
    warts
    -0.08
    POSITIVE LOGITS
    绣
    0.09
    _AST
    0.09
    ÑİÑģÑĮ
    0.09
    ensch
    0.09
    äºĮæľŁ
    0.09
    åıĪä¸Ģ次
    0.09
    ä¸Ĭä¸ĭ游
    0.08
    ORED
    0.08
    仲
    0.08
    AGON
    0.08
    Activations Density 0.007%

    No Known Activations