© 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. 39970
    Prev
    Next
    INDEX
    Explanations

    business activities and achievements

    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
    aches
    -0.08
    alic
    -0.08
    ä»ĺè´¹
    -0.08
    mov
    -0.08
    çªĦ
    -0.07
    æĶ¯ä»ĺ
    -0.07
    糯米
    -0.07
     mov
    -0.07
    éĢıè§Ĩ
    -0.07
    æľªæĪIJ年人
    -0.07
    POSITIVE LOGITS
     ìłľíĴĪ
    0.12
    è¡Įä¸ļåĨħ
    0.12
    çļĦ产åĵģ
    0.12
    为客æĪ·
    0.12
    客æĪ·éľĢæ±Ĥ
    0.11
    è¡Įä¸ļ
    0.11
    çŃīè¡Įä¸ļ
    0.11
    å·¥ç¨ĭæľºæ¢°
    0.11
    åİĤ家
    0.11
    ä¸ļåĨħ
    0.11
    Activations Density 0.307%

    No Known Activations