© 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. 10533
    Prev
    Next
    INDEX
    Explanations

    a descriptive word or noun

    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
    å±Ĥåĩºä¸įç©·
    -0.11
    çĵ¶åŃIJ
    -0.09
    å»ºåĽ½
    -0.09
    æĺĤ
    -0.09
    iju
    -0.09
    ivate
    -0.08
    .club
    -0.08
    æ»Ĥ
    -0.08
    zar
    -0.08
    çľĭä¼¼
    -0.08
    POSITIVE LOGITS
    åľºæīĢ
    0.12
     nơi
    0.12
    æ±ĩèģļ
    0.11
    æ¸Ĺ
    0.11
    èģļéĽĨ
    0.10
    åŃĺæĶ¾
    0.10
    ä½ķå¤Ħ
    0.10
    ä¹ĭåľ°
    0.10
     place
    0.10
     refuge
    0.10
    Activations Density 0.107%

    No Known Activations