© 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. 50695
    Prev
    Next
    INDEX
    Explanations

    track listing

    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
    宥
    -0.09
    æºIJæºIJä¸įæĸŃ
    -0.09
    éļ¾
    -0.09
    èĢĹè´¹
    -0.08
    被çĽĹ
    -0.08
    éĸĴ
    -0.08
    æĤ«
    -0.08
    éĺ²çĽĹ
    -0.08
    åŃ°
    -0.08
    çĽĹ
    -0.08
    POSITIVE LOGITS
    å¦Ĥä¸ĭ
    0.12
     details
    0.11
    详æĥħ
    0.10
    åĪ·
    0.10
    å®īæİĴ
    0.09
    yll
    0.09
    yr
    0.09
    (auto
    0.08
    details
    0.08
    åīĶ
    0.08
    Activations Density 0.066%

    No Known Activations