© 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. 21705
    Prev
    Next
    INDEX
    Explanations

    .edu and .gov domains

    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
    ened
    -0.08
    å¡ŀ
    -0.08
    ril
    -0.08
    ned
    -0.08
    åıĺå¾ĹæĽ´
    -0.08
    ttp
    -0.08
    bare
    -0.08
    ENUM
    -0.08
    egot
    -0.08
    nar
    -0.08
    POSITIVE LOGITS
    å¦Ĩ
    0.10
    .au
    0.10
    çĴŀ
    0.09
    antic
    0.09
    éĴ¹
    0.09
    蹶
    0.09
    ÑģÑĤавлен
    0.08
    ä¸įæĸŃåĪĽæĸ°
    0.08
    åħļå§Ķ
    0.08
    æĢģ
    0.08
    Activations Density 0.018%

    No Known Activations