© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8253
    Prev
    Next
    INDEX
    Explanations

    R or D followed by state abbreviation

    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
    çŃĶåį·
    -0.10
    éĻĭ
    -0.09
    å°±å¾Ī
    -0.09
    大çļĦ
    -0.09
    trag
    -0.09
    ailer
    -0.09
    ç¦ıå¾·
    -0.09
    å¸Ľ
    -0.08
    æ´¼
    -0.08
    æ´»çĿĢ
    -0.08
    POSITIVE LOGITS
    hana
    0.09
    ä¸įæİĴéĻ¤
    0.09
     Appet
    0.08
    åĺı
    0.08
    éĶ¦ç»£
    0.08
    æ±ĩ
    0.08
    åĵī
    0.08
    abar
    0.08
     Beds
    0.08
    è¤IJ
    0.07
    Activations Density 0.007%

    No Known Activations