© 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. 8111
    Prev
    Next
    INDEX
    Explanations

    first letter

    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
    ä¸ij
    -0.09
    æĤī
    -0.09
    è´«
    -0.09
    åĬ£
    -0.09
    ç©·
    -0.09
    ç¢į
    -0.09
    ifact
    -0.08
    ered
    -0.08
    onna
    -0.08
     unw
    -0.08
    POSITIVE LOGITS
     initials
    0.10
    è°IJ
    0.10
    迹
    0.09
    æľīèĥ½åĬĽ
    0.09
    ocha
    0.09
    avigation
    0.09
    æł¹æį®èĩªå·±
    0.09
    éļ½
    0.09
    å±ŀäºİèĩªå·±
    0.09
    èļ¤
    0.09
    Activations Density 0.022%

    No Known Activations