© 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. 30164
    Prev
    Next
    INDEX
    Explanations

    amino acid sequence

    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
    éĶĪ
    -0.10
    éĥ¨éĥ¨éķ¿
    -0.10
    abee
    -0.09
     bush
    -0.09
    :NO
    -0.09
    shaw
    -0.09
    assa
    -0.09
    è¾Ĺ
    -0.08
    uze
    -0.08
    ixe
    -0.08
    POSITIVE LOGITS
    çŃij
    0.10
    åįij
    0.09
    æł¼
    0.08
    éĻĩ
    0.08
    æ³Ĭ
    0.08
    ÙĨس
    0.08
    logged
    0.08
     Govern
    0.08
    潦
    0.08
    注
    0.08
    Activations Density 0.087%

    No Known Activations