© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20916
    Prev
    Next
    INDEX
    Explanations

    enough, perfectly, easy

    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
    ossa
    -0.10
    çĦ¦
    -0.09
    gor
    -0.09
    ä¸įåºĶ该
    -0.08
    å®īä¿Ŀ
    -0.08
    çĶĺ
    -0.08
    çľ·
    -0.08
    å¸ĤåľºèIJ¥éĶĢ
    -0.08
    ÑĦин
    -0.08
    åĻİ
    -0.08
    POSITIVE LOGITS
     enough
    0.17
     Enough
    0.13
    è¶³å¤ŁçļĦ
    0.13
    è¶³å¤Ł
    0.12
    å¾Īç®Ģåįķ
    0.11
    Enough
    0.11
     доÑģÑĤаÑĤоÑĩно
    0.10
     straightforward
    0.10
    illus
    0.10
    æľīè¶³å¤ŁçļĦ
    0.10
    Activations Density 0.042%

    No Known Activations