© 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. 23689
    Prev
    Next
    INDEX
    Explanations

    piston cylinder bore

    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
    æİ¥
    -0.09
     STL
    -0.09
     hel
    -0.09
    é¢Ĩ
    -0.09
    çĥ«
    -0.08
    cha
    -0.08
    çŃ¾è¯ģ
    -0.08
    atel
    -0.08
    æIJĤ
    -0.08
    ç´§å¯Ĩ
    -0.08
    POSITIVE LOGITS
     Challenger
    0.11
     slider
    0.10
    æĵİ
    0.09
    å¨ij
    0.09
    slider
    0.09
    å¾ģæĶ¶
    0.09
    è·ijæŃ¥
    0.09
    Junior
    0.09
     Slider
    0.09
    åĬ¨åijĺ
    0.09
    Activations Density 0.074%

    No Known Activations