© 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. 38192
    Prev
    Next
    INDEX
    Explanations

    accommodation, lodging, staying

    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
    æķ£
    -0.09
    æ³Ħ
    -0.09
    lect
    -0.08
    黳
    -0.08
    omal
    -0.08
    åĬŁ
    -0.08
    æ¨Ĭ
    -0.08
     mut
    -0.08
     ÑģÑĭÑĢ
    -0.08
    æĽ¹
    -0.08
    POSITIVE LOGITS
    ä½ı宿
    0.14
    æĪ¿éĹ´
    0.13
    宿èĪį
    0.12
     accommodation
    0.12
    å±ħä½ı
    0.12
    åį§å®¤
    0.12
    室åıĭ
    0.12
     accommodations
    0.12
    ä½ı
    0.12
     rooms
    0.11
    Activations Density 0.069%

    No Known Activations