© 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. 31270
    Prev
    Next
    INDEX
    Explanations

    rights to

    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
    éĻ¤æѤä¹ĭå¤ĸ
    -0.10
    ÙĨص
    -0.09
    orro
    -0.09
    家åĸ»
    -0.09
     McB
    -0.09
    ä¸Ģ对ä¸Ģ
    -0.09
    ially
    -0.08
    éĬ®
    -0.08
    缴è¾ĸ
    -0.08
     McCl
    -0.08
    POSITIVE LOGITS
    亲çĪ±
    0.09
     Coff
    0.09
    ä»
    0.09
     Wag
    0.08
    adio
    0.08
    acre
    0.08
    полн
    0.08
    eway
    0.08
    åľ¨äº¬
    0.08
    emic
    0.08
    Activations Density 0.008%

    No Known Activations