© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18190
    Prev
    Next
    INDEX
    Explanations

    temporal clauses

    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
    à¹Ģà¸ķ
    -0.09
    éĥ¦
    -0.09
    æ´
    -0.09
    ú
    -0.09
    å¦Ĥæľī
    -0.09
    ä»Ĭãģ¯
    -0.09
    åĢĺèĭ¥
    -0.08
    always
    -0.08
    å¦Ĥæŀľæĺ¯
    -0.08
    mlin
    -0.08
    POSITIVE LOGITS
    soever
    0.14
    abouts
    0.10
    ami
    0.09
    ë§Īëĭ¤
    0.09
    ith
    0.09
    对æĸ¹
    0.09
    å¾Ĺèµ·
    0.08
    æĨĶ
    0.08
    EVER
    0.08
    åħ¶éĹ´
    0.08
    Activations Density 0.102%

    No Known Activations