© 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. 53992
    Prev
    Next
    INDEX
    Explanations

    reported previously, seen on, implied by, isolated from

    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
    è¿Ļæĸ¹éĿ¢
    -0.10
    æīijåħĭ
    -0.09
    æıIJåīį
    -0.09
    ä¸įæĥ³
    -0.09
    æĸ¹éĿ¢çļĦ
    -0.09
    æĬij
    -0.09
    çĮ¬
    -0.09
    HING
    -0.09
    è±ģ
    -0.09
    åıijçĶŁåľ¨
    -0.09
    POSITIVE LOGITS
    为åĩĨ
    0.10
    åį´æĺ¯
    0.09
    OrDefault
    0.09
    çĶ¨äºİ
    0.09
     ones
    0.09
     used
    0.09
     wf
    0.08
    çļĦå®ŀéĻħ
    0.08
    çļĦéĤ£ç§į
    0.08
    ator
    0.08
    Activations Density 0.198%

    No Known Activations