© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51055
    Prev
    Next
    INDEX
    Explanations

    company names

    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
    sville
    -0.09
    åĩĨå¤ĩå·¥ä½ľ
    -0.09
    akedown
    -0.09
    Facade
    -0.09
    æĮ£
    -0.08
    群éĩĮ
    -0.08
    俱ä¹IJéĥ¨
    -0.08
    æľĭåıĭåľĪ
    -0.08
    å¤į
    -0.08
    oland
    -0.08
    POSITIVE LOGITS
     Solutions
    0.09
    åij·
    0.09
    çĶ¨è½¦
    0.09
     solutions
    0.09
    客æ°Ķ
    0.09
    داد
    0.09
    è¿ħ
    0.09
    æīĭå¥Ĺ
    0.09
    enco
    0.08
    æĪijå½ĵæŶ
    0.08
    Activations Density 0.186%

    No Known Activations