© 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. 50314
    Prev
    Next
    INDEX
    Explanations

    ratings and levels

    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
    èĥĮ
    -0.08
    åĹ£
    -0.08
    æ²īéĩį
    -0.08
    æ´ĭ
    -0.08
    æľķ
    -0.08
    обÑī
    -0.08
    ulsive
    -0.07
    èĽ¤
    -0.07
     Intr
    -0.07
     Rhodes
    -0.07
    POSITIVE LOGITS
    çŃī级
    0.24
    级åĪ«
    0.16
    åĽĽçº§
    0.13
    级åĪ«çļĦ
    0.13
    è¯Ħ级
    0.12
    æĺŁçº§
    0.12
     Rating
    0.12
    ä¸ī级
    0.12
     rating
    0.11
    级
    0.11
    Activations Density 0.058%

    No Known Activations