© 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. 33384
    Prev
    Next
    INDEX
    Explanations

    research and evidence

    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
    è¯Ī
    -0.09
    éra
    -0.09
    çĤ¹è¯Ħ
    -0.09
     Crowley
    -0.08
    ativ
    -0.08
    æ¼³
    -0.08
    çŃĸåĪĴ
    -0.08
     thợ
    -0.08
    èĩªä¿¡
    -0.08
    PTH
    -0.08
    POSITIVE LOGITS
    çłĶ究表æĺİ
    0.17
     studies
    0.13
     Studies
    0.11
    çłĶ究æĪIJæŀľ
    0.11
     proven
    0.11
    ç§ijåѦçłĶ究
    0.11
    Studies
    0.11
    表æĺİ
    0.10
     proved
    0.10
    çłĶ究
    0.09
    Activations Density 0.221%

    No Known Activations