© 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. 23448
    Prev
    Next
    INDEX
    Explanations

    stem cells

    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
    庸
    -0.11
    èĶ«
    -0.10
    æľįåĬ¡åĮº
    -0.10
    ä¸ĭæ²ī
    -0.09
    ietf
    -0.09
     Fernandez
    -0.09
    游泳
    -0.09
    antine
    -0.09
     underwater
    -0.09
    urma
    -0.09
    POSITIVE LOGITS
    寸
    0.11
    TabPage
    0.09
     Eve
    0.09
     Ober
    0.09
    æŁ¥çľĭæĽ´å¤ļ
    0.08
     Adam
    0.08
    空çĻ½
    0.08
    .JSON
    0.08
    åī¯æĢ»è£ģ
    0.08
    ides
    0.08
    Activations Density 0.126%

    No Known Activations