© 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. 32776
    Prev
    Next
    INDEX
    Explanations

    in place 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
    çij°
    -0.10
    ayne
    -0.09
    çĹĴ
    -0.09
     onto
    -0.08
    èĢĥè¯Ħ
    -0.08
    éĥİ
    -0.08
    æľīæīĢ
    -0.08
     USPS
    -0.08
    ä¿©
    -0.08
    ä¸įçĶĺ
    -0.08
    POSITIVE LOGITS
    ä»£æĽ¿
    0.26
    æĽ¿ä»£
    0.22
    åıĸ代
    0.21
     instead
    0.16
    à¹ģà¸Ĺà¸Ļ
    0.16
     вмеÑģÑĤ
    0.15
    æĽ¿æį¢
    0.15
    instead
    0.14
    æĽ¿
    0.13
     replaced
    0.13
    Activations Density 0.043%

    No Known Activations