© 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. 17209
    Prev
    Next
    INDEX
    Explanations

    road or roads and their condition/features

    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
     Mend
    -0.09
    erce
    -0.09
    erc
    -0.08
    idf
    -0.08
    soup
    -0.08
    åĽļ
    -0.08
    æīĢè°ĵçļĦ
    -0.08
    ள
    -0.08
    æľºç»Ħ
    -0.08
     Schw
    -0.08
    POSITIVE LOGITS
    ä¸Ĭæľī
    0.09
    建设工ç¨ĭ
    0.09
    ials
    0.09
    lets
    0.09
    åŁºå»º
    0.09
    aks
    0.09
    Shares
    0.09
    åħ¬å¼Ģ课
    0.08
    itions
    0.08
    夯å®ŀ
    0.08
    Activations Density 0.021%

    No Known Activations