© 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. 37928
    Prev
    Next
    INDEX
    Explanations

    fund for upgrades and costs

    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
    ayne
    -0.10
     Aub
    -0.10
    èĩªçĶ±
    -0.09
     Tob
    -0.09
     пÑĢинима
    -0.09
    ardin
    -0.08
    اÙħر
    -0.08
    kor
    -0.08
    æĻ´
    -0.08
    agic
    -0.08
    POSITIVE LOGITS
     Eins
    0.10
    çļĦä¸Ģéĥ¨åĪĨ
    0.09
    丰ç¡ķ
    0.09
    ä¸ķ
    0.09
    çīĩéĿ¢
    0.09
    æĪij以为
    0.09
    奸
    0.09
    èŁł
    0.08
    æĩĭ
    0.08
    ntag
    0.08
    Activations Density 0.023%

    No Known Activations