© 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. 51971
    Prev
    Next
    INDEX
    Explanations

    commanding words and phrases

    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
    漫
    -0.10
    ÑģÑĥ
    -0.10
    vey
    -0.09
    çīµ
    -0.09
    ç´§åĩij
    -0.09
    combat
    -0.09
    åĪ¶åº¦
    -0.09
    å§Ķ
    -0.09
    bish
    -0.09
    venida
    -0.09
    POSITIVE LOGITS
    eer
    0.15
    ingly
    0.11
    å±ĢéĿ¢
    0.11
    ä¹ĭåĬ¿
    0.10
    ä¹ĭ声
    0.10
    çľ¼çIJĥ
    0.09
    声èªī
    0.09
    èݺ
    0.09
    ments
    0.09
    ons
    0.09
    Activations Density 0.007%

    No Known Activations