© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59391
    Prev
    Next
    INDEX
    Explanations

    podcasts and pod::man specifications

    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
    Negative Logits
    liness
    -0.10
    æĥ¦
    -0.09
    ÑģÑı
    -0.09
    جة
    -0.09
    éĥħ
    -0.09
    åĢĴéľī
    -0.08
    å¸ĪèĮĥ大åѦ
    -0.08
    пÑĥÑĤ
    -0.08
    ichten
    -0.08
    anyl
    -0.08
    POSITIVE LOGITS
    ular
    0.12
    casts
    0.11
    ularity
    0.10
    czas
    0.10
    åįģä¸īäºĶ
    0.10
    ential
    0.10
    ailles
    0.09
    yssey
    0.09
    ç¾Ķ
    0.09
    ules
    0.09
    Activations Density 0.025%

    No Known Activations