© 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. 6999
    Prev
    Next
    INDEX
    Explanations

    squid caching proxy

    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
    åĪ°ä½į
    -0.10
    ç¿¡ç¿ł
    -0.09
    ç±į
    -0.09
    åįłé¢Ĩ
    -0.08
    çī§
    -0.08
    Binding
    -0.08
    è§ģåĪ°
    -0.08
    åİŁæĸĩåľ°åĿĢ
    -0.08
    çºłæŃ£
    -0.08
    微信群
    -0.08
    POSITIVE LOGITS
    á»įng
    0.10
    è¶ħæłĩ
    0.09
    é«ĺå°Ķ
    0.09
    äºĮ次
    0.09
    UCT
    0.09
    åĪ¸
    0.09
    代çIJĨ
    0.09
    edia
    0.09
    avour
    0.08
     proxies
    0.08
    Activations Density 0.155%

    No Known Activations