© 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. 48702
    Prev
    Next
    INDEX
    Explanations

    't any

    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
    çİij
    -0.12
    леж
    -0.10
    ä¸įçķĻ
    -0.10
    åħ¢
    -0.10
    rok
    -0.09
    éĢļ车
    -0.09
    趣
    -0.09
    对å¤ĸå¼ĢæĶ¾
    -0.09
    abbo
    -0.09
    çĴľ
    -0.09
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.09
    ä»»ä½ķ
    0.09
    rid
    0.09
    any
    0.09
     any
    0.09
    ç©°
    0.09
    ä¸Ģ大åłĨ
    0.08
    åĢŁçĶ¨
    0.08
     chop
    0.08
    æīĢè°ĵ
    0.08
    Activations Density 0.128%

    No Known Activations