© 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. 20806
    Prev
    Next
    INDEX
    Explanations

    big bang, universe, microwave background

    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
    æ¡£
    -0.11
    ç«ĭä½ĵ
    -0.10
    æī£
    -0.10
    åŁİéĻħ
    -0.10
    æIJģ
    -0.09
    æįįåį«
    -0.09
    红æĹĹ
    -0.09
    embro
    -0.09
    éĺ²å¾¡
    -0.09
    讣
    -0.09
    POSITIVE LOGITS
    6
    0.11
    9
    0.11
    8
    0.11
    æ··æ²Į
    0.10
    3
    0.10
    7
    0.10
    1
    0.10
    5
    0.10
    2
    0.10
    4
    0.10
    Activations Density 0.047%

    No Known Activations