© 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. 50352
    Prev
    Next
    INDEX
    Explanations

    introduces relative clauses or questions

    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
    éĤ£ä¹Īå¤ļ
    -0.09
    å°±åľ¨äºİ
    -0.09
    FromClass
    -0.08
    寥
    -0.08
    綦
    -0.08
    æ²®
    -0.08
    reh
    -0.08
    åĮĹ京åĨ¬å¥¥
    -0.08
    åīįåIJİ
    -0.08
    lod
    -0.08
    POSITIVE LOGITS
    é»ĺé»ĺ
    0.10
    ait
    0.10
    è§ĤæľĽ
    0.09
    äº
    0.09
     коÑĤоÑĢÑĭе
    0.08
    ulous
    0.08
    èİ·
    0.08
    .creation
    0.08
    彤
    0.08
    _VEC
    0.08
    Activations Density 0.106%

    No Known Activations