© 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. 36106
    Prev
    Next
    INDEX
    Explanations

    especially followed by adjective or for

    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
    è¨Ģè¯Ń
    -0.09
    åľ¨çĶŁæ´»ä¸Ń
    -0.09
    ä¸įä½Ĩ
    -0.09
    åĪĻ
    -0.08
    ural
    -0.08
    è¿ĺ
    -0.08
    mates
    -0.08
    å½ĵçĦ¶
    -0.08
    èĻ±
    -0.08
    Skip
    -0.08
    POSITIVE LOGITS
    رÙħ
    0.10
    èĢĥèĻijåĪ°
    0.10
    fy
    0.09
    antar
    0.09
    æľīçļĦ
    0.09
    æķıæĦŁ
    0.08
    纡
    0.08
    ä½Ĩä¸įéĻIJäºİ
    0.08
    ernet
    0.08
    atten
    0.08
    Activations Density 0.023%

    No Known Activations