© 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. 59039
    Prev
    Next
    INDEX
    Explanations

    profile management

    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
    ness
    -0.12
    fold
    -0.10
    çĦ¶æĺ¯
    -0.10
    Č
    -0.09
    orrow
    -0.09
    槿
    -0.09
    fir
    -0.09
    主æĦı
    -0.09
    ese
    -0.09
    orp
    -0.09
    POSITIVE LOGITS
    anst
    0.11
    agem
    0.10
    åĮĸçļĦ
    0.09
    edio
    0.09
    lements
    0.09
    Ùĩ
    0.09
    amiento
    0.09
    sed
    0.09
    OND
    0.09
    иÑĢÑĥем
    0.09
    Activations Density 0.025%

    No Known Activations