© 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. 35190
    Prev
    Next
    INDEX
    Explanations

    witnessed or witnessed

    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
     blink
    -0.09
    ëį°
    -0.09
    -found
    -0.08
    hi
    -0.08
    ir
    -0.08
     доÑĢог
    -0.08
     darauf
    -0.08
    Keywords
    -0.08
    bound
    -0.07
    ways
    -0.07
    POSITIVE LOGITS
    äºĨä¸Ģåľº
    0.12
    ä¸Ģå¹ķ
    0.11
     firsthand
    0.11
    å¥ĩ迹
    0.11
    æĤ²åī§
    0.10
    ä¸Ģåľº
    0.10
    çļĦåıijçĶŁ
    0.10
    å°ıå¹ħ
    0.10
    æĽ´å¤ļ精彩
    0.09
    éļ¾è¿ĩ
    0.09
    Activations Density 0.011%

    No Known Activations