© 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. 9628
    Prev
    Next
    INDEX
    Explanations

    direction and way

    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
    çѦ
    -0.09
    ÃŃstica
    -0.09
    roys
    -0.08
    ÙħاÙĦ
    -0.08
    allel
    -0.08
    计
    -0.08
    /jav
    -0.08
     ÑĦÑĥÑĤ
    -0.08
    Ä°M
    -0.08
    unker
    -0.08
    POSITIVE LOGITS
     direction
    0.11
    åıijå±ķè¶ĭåĬ¿
    0.11
    æĸ¹åIJij
    0.11
    åıijå±ķæĸ¹åIJij
    0.09
    çļĦè¶ĭåĬ¿
    0.09
    è¶ĭåĬ¿
    0.09
    åĽłåľ°åĪ¶å®ľ
    0.09
    çݺ
    0.09
    çļĦæĸ¹åIJij
    0.09
    帼
    0.09
    Activations Density 0.032%

    No Known Activations