© 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. 21752
    Prev
    Next
    INDEX
    Explanations

    considering or adjustment

    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
    çºĤ
    -0.10
    è°©
    -0.09
    AREN
    -0.09
    å¼ķèµ·äºĨ
    -0.09
    åIJĥäºĨ
    -0.09
    æĪĸèĢħåħ¶ä»ĸ
    -0.09
    æĹ¢æľī
    -0.09
    è·µ
    -0.09
    ä»ĸ表示
    -0.09
    åľ¨æĪijçļĦ
    -0.08
    POSITIVE LOGITS
    èĢĥèĻij
    0.15
     considering
    0.11
    èĢĥéĩı
    0.11
    èĢĥèĻijåĪ°
    0.11
     reck
    0.11
    èĢĥæħ®
    0.11
    åİ»æİī
    0.11
     consideration
    0.11
     considers
    0.10
     consider
    0.10
    Activations Density 0.100%

    No Known Activations