© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20852
    Prev
    Next
    INDEX
    Explanations

    by [name]

    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
    irit
    -0.09
    åĴ
    -0.09
     Hawkins
    -0.09
    éĥ¨åĪĨåľ°åĮº
    -0.09
    ä¸Ģ段
    -0.09
    段æŶéĹ´
    -0.08
    çIJ¥
    -0.08
     trib
    -0.08
    大çīĩ
    -0.08
    京éĥ½
    -0.08
    POSITIVE LOGITS
    è¿ĻæĶ¯
    0.10
    ·»
    0.10
    ÑĤол
    0.10
    ILE
    0.09
    çĹ¼
    0.09
    ocking
    0.09
     ÑįÑĤого
    0.09
    åģ·åģ·
    0.09
    ugh
    0.09
    cial
    0.09
    Activations Density 0.039%

    No Known Activations