© 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. 17635
    Prev
    Next
    INDEX
    Explanations

    implicit priming effects

    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
    çĶŁæĢģåľĪ
    -0.09
    æľĢä¼ĺ
    -0.09
    cit
    -0.09
    æįī
    -0.09
    åĵķ
    -0.09
     sacrific
    -0.09
    æīĭæĦŁ
    -0.09
     ÙĨÙĤ
    -0.08
    ç¦ĭ
    -0.08
    ilit
    -0.08
    POSITIVE LOGITS
    å¿ĥæĻº
    0.09
     Steele
    0.09
    mind
    0.09
     hypnot
    0.08
     conditioning
    0.08
    æĦıå¿Ĺ
    0.08
    mes
    0.08
     mind
    0.08
    大èĦij
    0.08
    å¨ĥå¨ĥ
    0.08
    Activations Density 0.116%

    No Known Activations