© 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. 37376
    Prev
    Next
    INDEX
    Explanations

    recommend this

    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¿ĺä¸įå¤Ł
    -0.09
    omite
    -0.09
    èѬ
    -0.09
    gles
    -0.09
    åĪĩ
    -0.08
    olute
    -0.08
    iously
    -0.08
    çħ²
    -0.08
    ija
    -0.08
    并éĿŀ
    -0.08
    POSITIVE LOGITS
    çĻ£
    0.09
    åħ¶ä»ĸ人
    0.09
    å°º
    0.09
     Acres
    0.09
    ä¸įåĩºæĿ¥
    0.08
     Tire
    0.08
    odia
    0.08
    å¯IJ
    0.08
    说åĩº
    0.08
    è¿Ļ家
    0.08
    Activations Density 0.006%

    No Known Activations