© 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. 10299
    Prev
    Next
    INDEX
    Explanations

    this [noun]

    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
    æ¸
    -0.10
    媳
    -0.09
    Insp
    -0.08
    çľŁç©º
    -0.08
    è¿ĻäºĽéĥ½æĺ¯
    -0.08
    /license
    -0.08
    æĽ°
    -0.08
    atorium
    -0.08
    aled
    -0.08
    vd
    -0.08
    POSITIVE LOGITS
    å¤Ļ
    0.10
    è¿Ļ项
    0.10
    è¿Ļç§įäºĭæĥħ
    0.09
    è¯īæ±Ĥ
    0.09
    éĢī项
    0.09
    å¾·å°Ķ
    0.09
     feature
    0.09
    çļ´
    0.09
    è¿Ļä¹Īåģļ
    0.09
    æŃ¤ä¸¾
    0.09
    Activations Density 0.181%

    No Known Activations