© 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. 18242
    Prev
    Next
    INDEX
    Explanations

    thin ice

    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
     Curl
    -0.09
     tons
    -0.09
     UNUSED
    -0.08
     اÙĦÙħاÙĦ
    -0.08
    è¶ħ
    -0.08
    loh
    -0.08
    å¤ļä½Ļ
    -0.08
    åIJĮèĥŀ
    -0.08
    ople
    -0.08
    rus
    -0.08
    POSITIVE LOGITS
    ç¼°
    0.11
    é£İåIJ¹
    0.11
     lá»Ńa
    0.11
    大æłij
    0.10
    æĶ¾è¿Ľ
    0.10
    çģ°å°ĺ
    0.10
    æĶ¾åħ¥
    0.10
    çģ«çĥ§
    0.10
    åĿļ硬
    0.09
    çī¢
    0.09
    Activations Density 0.263%

    No Known Activations