© 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. 36803
    Prev
    Next
    INDEX
    Explanations

    conjunctions and punctuation

    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
    é¢ĺ主
    -0.09
    éĥ¨ä»½
    -0.09
    ayne
    -0.08
    è²Įä¼¼
    -0.08
    åĥŃ
    -0.08
    çĦĵ
    -0.08
     bé
    -0.08
    罩
    -0.08
    亲çĪ±
    -0.08
    èĩªçĦ¶æĺ¯
    -0.08
    POSITIVE LOGITS
    è§īå¾Ĺå¾Ī
    0.12
    æħ¢æħ¢åľ°
    0.10
    raud
    0.10
    å¾Īå¥½åľ°
    0.09
    å°±å¾Ī
    0.09
    éĥ½å¾Ī
    0.09
    å¾Īéķ¿æŶéĹ´
    0.09
    ãģĻãģĶãģı
    0.09
    å¾Ĺå¾Ī
    0.09
     kind
    0.09
    Activations Density 0.109%

    No Known Activations