© 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. 7277
    Prev
    Next
    INDEX
    Explanations

    attempt to

    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
    娱
    -0.10
    æĶ¾è¿ĩ
    -0.09
    æľīçĽĬ
    -0.09
    æŃ¤äºº
    -0.09
    æľĭåıĭ
    -0.09
    ottage
    -0.08
    otte
    -0.08
    arris
    -0.08
    elle
    -0.08
    ertos
    -0.08
    POSITIVE LOGITS
    è°ĭ
    0.11
    è¬Ģ
    0.09
    abh
    0.09
     اÙĦسÙĬ
    0.08
    langs
    0.08
    à¸ģำ
    0.08
    å½»åºķ
    0.08
    è¦ģä¹Ī
    0.08
    æĬĬä»ĸ
    0.08
    win
    0.08
    Activations Density 0.066%

    No Known Activations