© 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. 8030
    Prev
    Next
    INDEX
    Explanations

    allegedly or suspected actions

    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
    _nil
    -0.10
    çŁ¥éģĵèĩªå·±
    -0.09
    بت
    -0.09
     воÑĤ
    -0.09
    åħĨ
    -0.09
    ÙĦاÙĨ
    -0.09
     IDR
    -0.08
    空çĻ½
    -0.08
    åħ¹
    -0.08
     destruct
    -0.08
    POSITIVE LOGITS
    çĸijä¼¼
    0.09
    æ¶īå«Į
    0.09
    æŃ£æĺ¯
    0.09
    ç¥ŀæĥħ
    0.09
    aux
    0.09
    ç´¯äºĨ
    0.09
    被çĽĹ
    0.09
    ä¸Ģå¹ķ
    0.09
    sic
    0.09
    æijĨæĶ¾
    0.08
    Activations Density 0.103%

    No Known Activations