© 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. 36195
    Prev
    Next
    INDEX
    Explanations

    some of

    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
     ones
    -0.09
     ÑģоÑģÑĤ
    -0.09
     Paula
    -0.08
    busters
    -0.08
    avior
    -0.08
     nowhere
    -0.08
    æ³®
    -0.08
     mostly
    -0.08
    没éĶĻ
    -0.08
    åĢĺ
    -0.08
    POSITIVE LOGITS
    æ£ł
    0.10
    æIJŀå¾Ĺ
    0.10
    -times
    0.10
    èĩªè´Ł
    0.09
    è¡Ļ
    0.09
    çłĶ究表æĺİ
    0.09
    onium
    0.09
    æĥħåĨµä¸ĭ
    0.09
    евиÑĩ
    0.09
     RCA
    0.08
    Activations Density 0.207%

    No Known Activations