© 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. 19502
    Prev
    Next
    INDEX
    Explanations

    adhesives, sealants, and liquids

    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
    dump
    -0.10
    绸
    -0.10
    åı®
    -0.09
    è®®äºĭ
    -0.09
    Dump
    -0.09
    å¹Ħ
    -0.08
    æľªæĪIJ
    -0.08
    å¨ĺ家
    -0.08
     dump
    -0.08
    æľī两个
    -0.08
    POSITIVE LOGITS
    åı¯çĶ¨äºİ
    0.11
    жд
    0.09
    èĥ´
    0.09
    ведиÑĤе
    0.08
    uling
    0.08
    å¼ķãģį
    0.08
    åIJİæŀľ
    0.08
    åķŃ
    0.08
    æŀ
    0.08
    éĢłèĪ¹
    0.08
    Activations Density 0.028%

    No Known Activations