© 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. 55970
    Prev
    Next
    INDEX
    Explanations

    reuse and reusability

    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
    ç»ķ
    -0.10
    ç¹ŀ
    -0.09
    éĩİçĶŁ
    -0.09
    èĥŃ
    -0.09
    æĭ¿èµ·
    -0.09
    OrDefault
    -0.09
     intptr
    -0.09
    é¾Ľ
    -0.08
    åĨ³å®ļäºĨ
    -0.08
    ÙĦÙĩ
    -0.08
    POSITIVE LOGITS
     reuse
    0.17
     reusable
    0.17
    reuse
    0.16
     reused
    0.15
    å¤ļ次
    0.13
    Reuse
    0.13
    Reusable
    0.12
    æ¯ı次
    0.11
    æĹłæķ°æ¬¡
    0.10
    æ¯ı次éĥ½
    0.10
    Activations Density 0.108%

    No Known Activations