© 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. 50586
    Prev
    Next
    INDEX
    Explanations

    ginger, cinnamon, gingival

    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
    åĴĮåľ°åĮº
    -0.13
    achine
    -0.09
    ä¸Ģä½ĵ
    -0.09
    orest
    -0.09
    ëģ¼
    -0.08
    ICODE
    -0.08
    amus
    -0.08
    ssf
    -0.08
    æºĸ
    -0.08
    æ¸ħæ¾Ī
    -0.08
    POSITIVE LOGITS
    åįģ足
    0.10
    bread
    0.09
    ered
    0.09
    ly
    0.09
    IPS
    0.09
    اء
    0.09
    alan
    0.08
    çľĩ
    0.08
    enuity
    0.08
    ering
    0.08
    Activations Density 0.006%

    No Known Activations