© 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. 2826
    Prev
    Next
    INDEX
    Explanations

    memory management and garbage collection

    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
    åŃļ
    -0.10
     Blind
    -0.10
    غا
    -0.09
     gag
    -0.09
    å£ģçĶ»
    -0.08
    åĽ½çİĭ
    -0.08
    å¿«æĬ¥
    -0.08
    æĸ¯å¡Ķ
    -0.08
    .addNode
    -0.08
    ä»İä¸ļ人åijĺ
    -0.08
    POSITIVE LOGITS
     resources
    0.11
    åĨħåŃĺ
    0.10
    RELEASE
    0.10
    éĩĬæĶ¾
    0.10
    麾
    0.10
     lif
    0.10
    çªĹå¤ĸ
    0.10
    èĩªçĦ¶èµĦæºIJ
    0.10
     memory
    0.09
    èµĦæºIJ
    0.09
    Activations Density 0.380%

    No Known Activations