© 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. 7500
    Prev
    Next
    INDEX
    Explanations

    quoted speech followed by explanation

    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
    HERE
    -0.10
    å°Ĭæķ¬
    -0.10
    mma
    -0.10
    âĺľ
    -0.10
    OKIE
    -0.09
    bsub
    -0.09
    LETE
    -0.09
    راÙħ
    -0.09
    eka
    -0.09
    æİĴæĸ¥
    -0.09
    POSITIVE LOGITS
    èµ·èįī
    0.08
    以åıĬåħ¶ä»ĸ
    0.08
    ä¸į失
    0.08
    likes
    0.08
    åĮ£
    0.08
    以åıĬ
    0.08
     ...
    0.08
     because
    0.07
    ä¸ĸçķĮä¸Ģæµģ
    0.07
    ä½Ĩä¸įéĻIJäºİ
    0.07
    Activations Density 0.239%

    No Known Activations