© 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. 4150
    Prev
    Next
    INDEX
    Explanations

    wondering if

    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
    _TestCase
    -0.09
    å½ĵçĦ¶
    -0.09
    æŃ£åĢ¼
    -0.09
    åľĪ
    -0.08
     tạm
    -0.08
    å¯Ĵ
    -0.08
    swer
    -0.08
    失åĪ©
    -0.08
    ä¿Ĺ
    -0.08
    ä»°
    -0.08
    POSITIVE LOGITS
    /how
    0.11
    å¾Ĺèµ·
    0.10
    ught
    0.10
    Invariant
    0.10
    rish
    0.10
    ä¼ļå¼ķèµ·
    0.10
    æľīä»»ä½ķ
    0.09
    è¿Ļè¾ĪåŃIJ
    0.09
    æĹŃ
    0.09
    ä¼ļåĩºçİ°
    0.09
    Activations Density 0.039%

    No Known Activations