© 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. 39483
    Prev
    Next
    INDEX
    Explanations

    Littlewoods, Sansarg, Agoda, Top Shelf, FirstLight, StandWithUs, Houzz, Save the Children, Untappd, Flybe

    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
    以人æ°ij
    -0.08
     вÑĢемен
    -0.08
     predictable
    -0.08
    è¿Ķ乡
    -0.08
    æ½ĩ
    -0.07
    è®®é¢ĺ
    -0.07
    çĶŁé²ľ
    -0.07
    æľįåĬ¡åĮº
    -0.07
    æģ¼
    -0.07
     lem
    -0.07
    POSITIVE LOGITS
    å¹³åı°ä¸Ĭ
    0.12
    åıĭ们
    0.11
    å¹³åı°
    0.09
    æį©
    0.09
    оÑĩки
    0.09
    -approved
    0.08
    ãģĹãģ¾
    0.08
    -selected
    0.08
    èľĤ
    0.08
     proporcion
    0.08
    Activations Density 0.100%

    No Known Activations