© 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. 54378
    Prev
    Next
    INDEX
    Explanations

    added

    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
    æ±ľ
    -0.09
    ubo
    -0.08
    older
    -0.08
    owi
    -0.08
    æĽĿ
    -0.08
    plain
    -0.08
    ISM
    -0.08
    оÑĢа
    -0.08
    amon
    -0.08
    éri
    -0.08
    POSITIVE LOGITS
     added
    0.15
    -added
    0.14
    added
    0.14
    æ·»åĬł
    0.14
     æ·»åĬł
    0.14
    .addTo
    0.12
    æ·»
    0.12
     добав
    0.12
     addTo
    0.11
    åĬłåħ¥äºĨ
    0.11
    Activations Density 0.100%

    No Known Activations