© 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. 17566
    Prev
    Next
    INDEX
    Explanations

    take these, take up

    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
    姹
    -0.10
    æ²IJæµ´
    -0.09
    åĭĥ
    -0.09
    so
    -0.08
    çķĻä¸ĭ
    -0.08
    sy
    -0.08
    enes
    -0.08
    ç¡®
    -0.08
    åģļå¾Ĺ
    -0.08
    lay
    -0.08
    POSITIVE LOGITS
    æĪĹ
    0.10
    ä¸Ģäºĭ
    0.10
    ä¸į稳å®ļ
    0.09
    ä¼Ļ
    0.09
    åħ¬çĽĬæ´»åĬ¨
    0.09
    igte
    0.09
    èIJĥ
    0.09
    没éĶĻ
    0.09
    è¿©
    0.08
     BaseType
    0.08
    Activations Density 0.020%

    No Known Activations