© 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. 62684
    Prev
    Next
    INDEX
    Explanations

    neural networks and circuits

    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
    人çļĦ
    -0.09
    å¦ĥ
    -0.09
    人å¿ĥ
    -0.09
    让æ¶Īè´¹èĢħ
    -0.09
    æºħ
    -0.09
    çª
    -0.09
    ä¸įéľĢè¦ģ
    -0.09
    æĥŁ
    -0.08
     deck
    -0.08
    æį§
    -0.08
    POSITIVE LOGITS
    åĵºä¹³
    0.09
    etur
    0.09
    FromArray
    0.09
    etr
    0.09
     silenced
    0.08
    åŀĵ
    0.08
    ectl
    0.08
    åĬŁ
    0.08
     SAC
    0.08
    âľĵ
    0.08
    Activations Density 0.466%

    No Known Activations