© 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. 21610
    Prev
    Next
    INDEX
    Explanations

    can't be trusted or relied upon

    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
     beaut
    -0.10
    enic
    -0.09
    éħ±
    -0.09
    å¤įåħ´
    -0.08
     formally
    -0.08
    æ½ľ
    -0.08
    è¢Ĥ
    -0.08
     mou
    -0.08
    äºĨä¸Ģåľº
    -0.08
    æĬij
    -0.08
    POSITIVE LOGITS
    åı¯éĿł
    0.32
    åı¯éĿłçļĦ
    0.29
    ä¿¡èµĸ
    0.28
    åı¯éĿłæĢ§
    0.28
    ä¿¡ä»»
    0.27
    åı¯ä¿¡
    0.27
     reliable
    0.25
     reliability
    0.23
     trustworthy
    0.23
     Reliable
    0.21
    Activations Density 0.078%

    No Known Activations