© 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. 10271
    Prev
    Next
    INDEX
    Explanations

    physical addresses and locations

    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
    logue
    -0.11
    ä¾Ī
    -0.10
    ä¸Ģåı°
    -0.10
    éł»éģĵ
    -0.10
    æĢģ
    -0.10
    reich
    -0.10
    arro
    -0.10
    æ¡ĪåŃIJ
    -0.09
    ä¸į解
    -0.09
    æŀ¶åŃIJ
    -0.09
    POSITIVE LOGITS
    åľ°åĿĢ
    0.13
     address
    0.12
     getAddress
    0.11
    (Address
    0.10
    ä½ıåĿĢ
    0.10
     Address
    0.10
     адÑĢеÑģ
    0.10
    address
    0.10
    æĶ¶
    0.09
     addresses
    0.09
    Activations Density 0.033%

    No Known Activations