© 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. 8251
    Prev
    Next
    INDEX
    Explanations

    stable characteristics

    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
    éĹ®ä»ĸ
    -0.09
    è¶Ļ
    -0.09
    elder
    -0.09
    ç±³å°Ķ
    -0.09
    æĶ¾ç¼ĵ
    -0.09
    åĩ¡æľ¬ç½ij
    -0.08
    å¿Ļ
    -0.08
    åĮĨåĮĨ
    -0.08
     menn
    -0.08
    ä½łè¿ĺ
    -0.08
    POSITIVE LOGITS
    稳å®ļ
    0.11
     stable
    0.10
    ç¾İè§Ĥ
    0.09
    ê¶Į
    0.09
    åħ¨èĥ½
    0.08
    çĻ¾åĪĨä¹ĭ
    0.08
    产éĶĢ
    0.08
    stable
    0.08
    æľīè¶³å¤ŁçļĦ
    0.08
    æ°ijæĹı
    0.08
    Activations Density 0.160%

    No Known Activations