© 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. 19179
    Prev
    Next
    INDEX
    Explanations

    simply click on

    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
    è¿Ķ
    -0.10
    ottes
    -0.09
    ä¹Łåıªèĥ½
    -0.09
    ç¼ĸç»ĩ
    -0.09
    è¿Ľä¸ĢæŃ¥
    -0.09
    ä¸įåľ¨
    -0.09
    ä¸įåĨįæĺ¯
    -0.09
    çIJĩ
    -0.09
    ä¹Łåıªæľī
    -0.09
    åıªå¥½
    -0.09
    POSITIVE LOGITS
    éļı便
    0.11
    èĤĵ
    0.11
    éļıå¤Ħ
    0.10
    éļıæĦı
    0.10
    åĸĬ
    0.10
    ola
    0.09
    çĽ²
    0.09
    Thor
    0.09
    åĪĴ
    0.09
    åıijæĮ¥äºĨ
    0.09
    Activations Density 0.092%

    No Known Activations