© 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. 22914
    Prev
    Next
    INDEX
    Explanations

    fuel systems

    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
    åħ«åįģ
    -0.10
    åİħ
    -0.10
    ä¸Ģæłĭ
    -0.10
    çªį
    -0.09
    ç¬ĭ
    -0.09
    åĽĽåįģ
    -0.09
    温室
    -0.09
    骤
    -0.09
    çĦĻ
    -0.09
    çĶµæ¢¯
    -0.09
    POSITIVE LOGITS
     gasoline
    0.09
    æ²½
    0.09
    kap
    0.09
     mixture
    0.09
    åıĪèĥ½
    0.09
    andum
    0.09
    åĪ¶åº¦æĶ¹éĿ©
    0.09
    iesen
    0.09
    好åIJĹ
    0.08
    apor
    0.08
    Activations Density 0.061%

    No Known Activations