© 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. 57070
    Prev
    Next
    INDEX
    Explanations

    helpful and useful for

    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
    æľīä¿¡å¿ĥ
    -0.11
    ä¸ĩäºĭ
    -0.11
    å²ĺ
    -0.10
    edList
    -0.10
    éĽĩ
    -0.09
    èģĺ请
    -0.09
    å»ĵ
    -0.09
    æŀĭ
    -0.09
    ready
    -0.09
    boom
    -0.09
    POSITIVE LOGITS
    è¿Ļ对äºİ
    0.12
    çī¹åĪ«æĺ¯åľ¨
    0.11
    çĶ¨éĢĶ
    0.11
    便åĪ©
    0.10
    å°¤åħ¶
    0.10
     useful
    0.10
    çī¹åĪ«æĺ¯
    0.10
    å½ĵä½ł
    0.10
    æĸ¹ä¾¿
    0.09
    å°¤åħ¶æĺ¯
    0.09
    Activations Density 0.225%

    No Known Activations