© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11296
    Prev
    Next
    INDEX
    Explanations

    bed or beds

    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
    VERSE
    -0.09
    森
    -0.09
    Lens
    -0.09
    é¹ĺ
    -0.09
    éĢį
    -0.09
    LING
    -0.09
    åĢ¾
    -0.09
    olith
    -0.08
    ERSION
    -0.08
    åĹĵ
    -0.08
    POSITIVE LOGITS
    åºĬ
    0.21
    åºĬä¸Ĭ
    0.19
     bed
    0.18
     beds
    0.17
    bed
    0.16
    åľ¨åºĬä¸Ĭ
    0.16
    åºĬä½į
    0.15
    榻
    0.15
     Bed
    0.15
    -bed
    0.15
    Activations Density 0.037%

    No Known Activations