© 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. 21772
    Prev
    Next
    INDEX
    Explanations

    ranking and awards

    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
    åħ±éĿĴåĽ¢
    -0.09
     brow
    -0.09
    chair
    -0.08
    çī¹æĸ¯
    -0.08
    离
    -0.08
     chair
    -0.08
    astics
    -0.08
    åľ¨åĽ½å¤ĸ
    -0.08
     xlink
    -0.08
    äºĶå®ĺ
    -0.08
    POSITIVE LOGITS
    æ¦ľåįķ
    0.15
    è¯Ħæ¯Ķ
    0.13
    è¯ĦéĢī
    0.12
    æ¦ľ
    0.12
    èŤ
    0.11
     rankings
    0.10
    è¡¡éĩı
    0.10
    çĻ¾å¼º
    0.10
    åĩºçĤī
    0.10
    æİĴè¡Įæ¦ľ
    0.10
    Activations Density 0.082%

    No Known Activations