© 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. 7916
    Prev
    Next
    INDEX
    Explanations

    room / rooms

    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
     sidewalk
    -0.10
    两家
    -0.09
    metro
    -0.09
     Hog
    -0.09
    Metro
    -0.09
     Metro
    -0.09
    .sourceforge
    -0.09
    _near
    -0.09
    ledged
    -0.08
    InnerHTML
    -0.08
    POSITIVE LOGITS
    浴室
    0.12
     room
    0.11
    室
    0.11
     rooms
    0.11
    æĪ¿éĹ´
    0.11
    åħ³
    0.10
    room
    0.10
     Room
    0.10
    客æĪ¿
    0.10
    _room
    0.09
    Activations Density 0.246%

    No Known Activations