© 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. 18703
    Prev
    Next
    INDEX
    Explanations

    break up

    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
    éļħ
    -0.09
    elix
    -0.09
    ä¸įåı¯èĥ½
    -0.08
     пÑĥнк
    -0.08
    edef
    -0.08
     trụ
    -0.08
    akeup
    -0.08
    endar
    -0.08
    ombat
    -0.08
    è¡®
    -0.08
    POSITIVE LOGITS
    çĿ¬
    0.10
    åĽ«
    0.09
    fen
    0.09
    ï¸
    0.09
    è¹ī
    0.09
    佬
    0.09
    itial
    0.09
    æ³IJ
    0.09
    è¾Ļ
    0.09
    gle
    0.09
    Activations Density 0.005%

    No Known Activations