© 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. 58783
    Prev
    Next
    INDEX
    Explanations

    explanation of the beginning of sentences

    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
    Ñģел
    -0.08
    ä¸Ģæĸ¹éĿ¢æĺ¯
    -0.08
    æĶ¯æŁ±
    -0.08
    (comment
    -0.08
    ASF
    -0.08
    çĭ®
    -0.07
    éļıåį³
    -0.07
    éĤ£æĺ¯
    -0.07
    æºľ
    -0.07
    æĹłçĸijæĺ¯
    -0.07
    POSITIVE LOGITS
    å½ĵäºĭ
    0.09
    ìħĪ
    0.09
    æ§ĺ
    0.09
    liers
    0.09
    强è°ĥ
    0.09
    amespace
    0.08
    å½ĵäºĭ人
    0.08
    åģļä¸įåĪ°
    0.08
    -et
    0.08
    ä¹Łä¸įè¦ģ
    0.08
    Activations Density 0.443%

    No Known Activations