© 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. 8445
    Prev
    Next
    INDEX
    Explanations

    cabinet space

    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
    é©°æı´
    -0.09
     reprodu
    -0.09
    åįıè®®
    -0.09
    æĹģ
    -0.09
    ilon
    -0.08
    æ¶ī
    -0.08
     Conspiracy
    -0.08
    çķħ
    -0.08
     Luca
    -0.08
     Couple
    -0.08
    POSITIVE LOGITS
    åħ®
    0.10
    locks
    0.10
    带åĬ¨
    0.10
    æ©±æŁľ
    0.10
    æŁľ
    0.10
    abinet
    0.09
     cabinets
    0.09
    è¡£æŁľ
    0.09
    æĢ»ä»·
    0.09
    ัย
    0.09
    Activations Density 0.077%

    No Known Activations