© 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. 53001
    Prev
    Next
    INDEX
    Explanations

    hay and alfalfa

    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
    uko
    -0.10
    raud
    -0.09
    ippo
    -0.09
    æ¶ī
    -0.09
    ele
    -0.09
    åĸĦæĦı
    -0.09
    æľĢéķ¿
    -0.08
    å§ĭç»Ī
    -0.08
    hip
    -0.08
    Mur
    -0.08
    POSITIVE LOGITS
    sut
    0.09
    vern
    0.09
    çĢĽ
    0.08
    åķ¬
    0.08
    åķ¾
    0.08
    éļ¶å±ŀ
    0.08
    èĩĬ
    0.08
     вÑģÑıк
    0.08
    åľ¨å¤ĸ
    0.08
    èµ
    0.08
    Activations Density 0.009%

    No Known Activations