© 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. 26939
    Prev
    Next
    INDEX
    Explanations

    matlab, matplotlib, maternity, matric

    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
    涯
    -0.11
     подÑĢоб
    -0.09
     nhiá»ĩm
    -0.09
    erman
    -0.09
     Incre
    -0.09
    èĬ
    -0.09
    æłĩå¿ĹæĢ§
    -0.08
    har
    -0.08
    çĪº
    -0.08
    edList
    -0.08
    POSITIVE LOGITS
    ernity
    0.13
    ricula
    0.12
    mates
    0.12
    ting
    0.12
    иÑĢование
    0.11
    riz
    0.11
    uration
    0.11
    rices
    0.10
    mate
    0.10
    tern
    0.10
    Activations Density 0.023%

    No Known Activations