© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 54952
    Prev
    Next
    INDEX
    Explanations

    crash incidents and analysis

    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
    ities
    -0.13
    istic
    -0.11
    ized
    -0.10
    eut
    -0.10
    侧ç»ĵæŀĦæĢ§
    -0.10
    ize
    -0.10
    ihan
    -0.09
    建åĨĽ
    -0.09
    主ä¹ī
    -0.09
    standing
    -0.09
    POSITIVE LOGITS
    ingly
    0.13
    able
    0.11
    ëģĶ
    0.11
    第ä¸Ģ书记
    0.10
    аÑİÑĤÑģÑı
    0.10
    æ»ĵ
    0.10
    管å§Ķä¼ļ
    0.10
    nable
    0.09
    رÙĬد
    0.09
    ABLE
    0.09
    Activations Density 0.009%

    No Known Activations