© 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. 1232
    Prev
    Next
    INDEX
    Explanations

    air, water, condensation, vapor

    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
    egg
    -0.10
    è¡Ĺ
    -0.09
    èĩªæѤ
    -0.09
    æįIJèµł
    -0.08
    æĬ¬
    -0.08
    åĤ¬
    -0.08
    å¯Ĥ
    -0.08
    çĩĥçĥ§
    -0.08
     Hem
    -0.08
    ayo
    -0.08
    POSITIVE LOGITS
     dew
    0.11
    åIJIJ
    0.10
    æīĢæīĢ
    0.09
    ç¬ĶèĢħ
    0.09
     Angels
    0.08
    家åºŃæķĻèĤ²
    0.08
    éĴĵ
    0.08
    åĪ¶
    0.08
     cond
    0.08
    åĨ·éĵ¾
    0.08
    Activations Density 0.035%

    No Known Activations