© 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. 57892
    Prev
    Next
    INDEX
    Explanations

    philanthropic contributions

    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
    bens
    -0.10
    沿
    -0.09
    温室
    -0.09
    çĥŃ线
    -0.09
    顺çĿĢ
    -0.08
    ÑĪки
    -0.08
    .abs
    -0.08
    æī¿
    -0.08
    سط
    -0.08
    uala
    -0.08
    POSITIVE LOGITS
    æįIJèµł
    0.18
    æįIJ
    0.14
    èµł
    0.12
    æįIJåĬ©
    0.11
    æįIJ款
    0.11
    æįIJçĮ®
    0.11
    é¦Ī
    0.11
     donated
    0.10
     donations
    0.10
     donation
    0.10
    Activations Density 0.067%

    No Known Activations