© 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. 4309
    Prev
    Next
    INDEX
    Explanations

    goes or went

    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
    å¥ij
    -0.10
    æľªçŁ¥
    -0.10
    举äºļ
    -0.09
    èĮ¹
    -0.09
    olla
    -0.09
    ä¸īåĨľ
    -0.09
    onga
    -0.09
    éĩĬ
    -0.09
    ÄĻd
    -0.08
    æ²®
    -0.08
    POSITIVE LOGITS
    åĽºå®ļçļĦ
    0.09
    çĢij
    0.09
    ih
    0.08
    abee
    0.08
    屿
    0.08
    pai
    0.08
    æ¡Ģ
    0.08
    èµ·æĿ¥
    0.08
    浸
    0.08
    ascar
    0.08
    Activations Density 0.060%

    No Known Activations