© 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. 62923
    Prev
    Next
    INDEX
    Explanations

    absorb and absorption

    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
    çļĦçģµéŃĤ
    -0.09
    WISE
    -0.08
    æ±°
    -0.08
    éĺ²èħIJ
    -0.08
    åĤ¬
    -0.08
    çļĦçĶŁåij½
    -0.08
    çĭł
    -0.08
     lẽ
    -0.08
    è¯ĦéĢī
    -0.08
     cola
    -0.08
    POSITIVE LOGITS
     absorb
    0.13
    åIJ¸æĶ¶
    0.13
    åIJ¸çº³
    0.13
    海绵
    0.11
    .Abs
    0.10
     absorption
    0.10
    æ¾į
    0.10
    abs
    0.10
    åĬłåĢį
    0.10
    ä¹Ĵä¹ĵ
    0.10
    Activations Density 0.040%

    No Known Activations