© 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. 38247
    Prev
    Next
    INDEX
    Explanations

    evicted, closing, demolition, heroes

    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
    åĩıè½»
    -0.11
     дÑĥÑħов
    -0.10
    带åĽŀ
    -0.10
    \Queue
    -0.10
    éĻį
    -0.10
    æ¼Ĥæµģ
    -0.09
    æ¶Īè´¹åĵģ
    -0.09
    è§IJ
    -0.09
    _strerror
    -0.09
    æĬĬæīĭ
    -0.09
    POSITIVE LOGITS
    æĭĨè¿ģ
    0.16
    æIJ¬è¿ģ
    0.13
    èħ¾
    0.11
    æĭĨéĻ¤
    0.11
     displacement
    0.11
    æ¯ģ
    0.11
    æIJ¬å®¶
    0.10
    éĢ¼
    0.10
    强è¡Į
    0.10
     eviction
    0.10
    Activations Density 0.073%

    No Known Activations