© 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. 23934
    Prev
    Next
    INDEX
    Explanations

    recalling experiences or information

    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
    æľ¬è½®
    -0.12
    å§ĭç»Īä¿ĿæĮģ
    -0.11
    æľ¬æ¬¡
    -0.10
    èĥ½çľĭåĩº
    -0.10
    ç»ĵæŀĦè°ĥæķ´
    -0.09
    个人è§ĤçĤ¹
    -0.09
    仲
    -0.09
    èĭ±æīį
    -0.09
    è°Ķ
    -0.09
    éĢģåĩº
    -0.09
    POSITIVE LOGITS
    åĪ»æĦı
    0.09
    èµ°
    0.09
    égor
    0.09
    éĤ£ä¹Ī
    0.08
     sandwich
    0.08
    å¾Ģ
    0.08
    çĿĢ
    0.08
    åİĭæĬij
    0.08
     advoc
    0.08
    ocol
    0.08
    Activations Density 0.236%

    No Known Activations