© 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. 52913
    Prev
    Next
    INDEX
    Explanations

    private room or space

    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
    åľ¨è·¯ä¸Ĭ
    -0.12
    è·¯ä¸Ĭ
    -0.10
    Escort
    -0.10
     обÑīеÑģÑĤв
    -0.10
    京åŁİ
    -0.10
    æĮĩå°ĸ
    -0.10
    伶
    -0.10
    ipple
    -0.10
     stadiums
    -0.10
    éģĵè·¯ä¸Ĭ
    -0.09
    POSITIVE LOGITS
    室åĨħ
    0.14
    æ°Ķæ°Ľ
    0.13
    客åİħ
    0.13
    å¢Ļå£ģ
    0.13
    榻
    0.13
    åį§å®¤
    0.11
    åľ¨éĩĮéĿ¢
    0.11
    室
    0.11
     floor
    0.11
    æĪ¿éĹ´
    0.11
    Activations Density 0.310%

    No Known Activations