© 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. 27133
    Prev
    Next
    INDEX
    Explanations

    learning and memorization

    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
    éŵ
    -0.10
    omba
    -0.10
    /animations
    -0.10
    âĺ°
    -0.10
    åĬŀ
    -0.09
    æ½®æµģ
    -0.09
    æľīéĴ±
    -0.09
     créd
    -0.09
    çłľ
    -0.09
    éĹ®éĹ®
    -0.09
    POSITIVE LOGITS
    è®°å¿Ĩ
    0.14
     memor
    0.13
    ä¸Ģéģį
    0.12
    çī¢è®°
    0.12
    çĨŁ
    0.12
    è®°å¿ĨåĬĽ
    0.12
    èĥĮ
    0.11
     memory
    0.11
    诵
    0.11
    ä¸Ģ段
    0.10
    Activations Density 0.027%

    No Known Activations