© 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. 18756
    Prev
    Next
    INDEX
    Explanations

    vote or referendum

    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
    ä¸īæĸ¹
    -0.09
    çĦ¦
    -0.09
    楼ä¸Ĭ
    -0.09
    åħĦå¼Ł
    -0.08
    åľ£è¯ŀ
    -0.08
    èİ«
    -0.08
    aura
    -0.08
    ypy
    -0.08
    ills
    -0.08
    æħĭ
    -0.08
    POSITIVE LOGITS
    æĬķ票
    0.14
    表åĨ³
    0.13
     vote
    0.12
    ä¸Ģåľº
    0.11
     голоÑģ
    0.10
     referendum
    0.10
     votes
    0.10
    votes
    0.10
     voting
    0.09
    å°±è¿ij
    0.09
    Activations Density 0.087%

    No Known Activations