© 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. 34916
    Prev
    Next
    INDEX
    Explanations

    lists items separated by commas and "and"

    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
    åı¯ä¾Ľ
    -0.10
    ÑĢон
    -0.08
     Lama
    -0.08
    ORN
    -0.08
    ä¸ĭè°ĥ
    -0.08
    angent
    -0.07
    æŸ
    -0.07
     PART
    -0.07
    icht
    -0.07
    /group
    -0.07
    POSITIVE LOGITS
    å¾ĹçĽĬäºİ
    0.10
    æĬĹ
    0.10
    åĮĸ解
    0.10
    æݪæĸ½
    0.10
    è¿ĻçĤ¹
    0.09
    æĢ§èĥ½
    0.09
    è¿ĺèĥ½
    0.09
    arness
    0.09
    IMIT
    0.09
    å®ĥçļĦ
    0.09
    Activations Density 0.139%

    No Known Activations