© 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. 54612
    Prev
    Next
    INDEX
    Explanations

    flooring and surfaces

    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¤ħ
    -0.10
    åĪ©åĻ¨
    -0.10
    nest
    -0.09
    ä¸Ģä½ĵ
    -0.09
    åĶ¯
    -0.09
    ILLED
    -0.09
    èµĦ
    -0.09
    毡
    -0.09
    æīĵéĢłæĪIJ
    -0.09
    PLY
    -0.09
    POSITIVE LOGITS
    çģ°
    0.09
    ç²²
    0.08
    ife
    0.08
    æŃ¹
    0.08
    åĪ·
    0.08
     triple
    0.08
     everywhere
    0.08
    èIJľ
    0.08
     Choi
    0.08
    大éĥ¨åĪĨ
    0.07
    Activations Density 0.047%

    No Known Activations