© 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. 52754
    Prev
    Next
    INDEX
    Explanations

    saved money or time

    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¯ħ
    -0.09
    è¶Ĭ
    -0.09
    æģ°
    -0.09
    åįıåĬ©
    -0.09
    ãģıãĤĭ
    -0.09
    离
    -0.08
    å®īç½®
    -0.08
    ifu
    -0.08
    赦
    -0.08
    äºıæįŁ
    -0.08
    POSITIVE LOGITS
    ä¸įå¿ħè¦ģçļĦ
    0.14
    éģ¿åħį
    0.13
    å®Ŀè´µ
    0.10
    缸å½ĵ
    0.10
     khá»ıi
    0.10
    åı¯èĥ½åĩºçİ°
    0.10
    å®Ŀè´µçļĦ
    0.09
     unnecessary
    0.09
    ounded
    0.09
     otherwise
    0.09
    Activations Density 0.039%

    No Known Activations