© 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. 61717
    Prev
    Next
    INDEX
    Explanations

    absorption and bioavailability

    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
    ä¸įæŃ»
    -0.09
     certo
    -0.09
    _compress
    -0.09
    .setInput
    -0.09
    rown
    -0.08
    oub
    -0.08
     ÑģовеÑĢÑĪен
    -0.08
    neau
    -0.08
    èĩªåıij
    -0.08
    ycled
    -0.08
    POSITIVE LOGITS
    åIJ¸æĶ¶
    0.15
    æ¶ĪåĮĸ
    0.12
    çIJĨ解åĴĮ
    0.12
    åIJ¸åıĸ
    0.10
    æĽ´å®¹æĺĵ
    0.10
     digestion
    0.10
     absorption
    0.10
    éĢģè¾¾
    0.10
    æ±²åıĸ
    0.10
    Abs
    0.10
    Activations Density 0.211%

    No Known Activations