© 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. 18317
    Prev
    Next
    INDEX
    Explanations

    settlement and legal disputes

    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
    obic
    -0.09
    æı´
    -0.09
    noinspection
    -0.09
    specs
    -0.09
    ä»İæѤ
    -0.08
    alic
    -0.08
    orum
    -0.08
     arrest
    -0.08
    onaut
    -0.08
    eka
    -0.08
    POSITIVE LOGITS
    éĺħ读åħ¨æĸĩ
    0.10
    ä¸Ģç¬Ķ
    0.10
    è¿Ļäºĭ
    0.10
    æ¶Īæģ¯
    0.09
    ADOW
    0.09
    åı¯è¡ĮæĢ§
    0.08
    å´´
    0.08
    TING
    0.08
    ien
    0.08
    ting
    0.08
    Activations Density 0.007%

    No Known Activations