© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53068
    Prev
    Next
    INDEX
    Explanations

    salvage timber

    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
    æĥ©
    -0.09
    çĽ¸ä¿¡
    -0.09
    nearest
    -0.09
    ç¶ĵéģİ
    -0.08
    _va
    -0.08
    æĹ¥çĽĬ
    -0.08
    åĽŀåĪ°å®¶
    -0.08
    æºIJæºIJ
    -0.08
    AVA
    -0.08
    pet
    -0.08
    POSITIVE LOGITS
    ãģĹãģ¦ãģĬãģı
    0.20
    æıIJåīį
    0.18
    æıIJæĹ©
    0.16
    å°½æĹ©
    0.13
    ãģ¦ãģĬãģı
    0.13
    é¢ĦåħĪ
    0.12
    åīįçŀ»æĢ§
    0.12
    åĤ¨å¤ĩ
    0.12
    åĩĨå¤ĩ好
    0.12
     preempt
    0.12
    Activations Density 0.088%

    No Known Activations