© 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. 30863
    Prev
    Next
    INDEX
    Explanations

    laxity and lapse

    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
    AMY
    -0.09
    liness
    -0.08
    åĶ¾
    -0.08
    jected
    -0.08
    åĪĨæĶ¯
    -0.08
    æĸ°å±ĢéĿ¢
    -0.08
    åĪĨæѧ
    -0.08
    gest
    -0.08
    ainment
    -0.08
    alker
    -0.08
    POSITIVE LOGITS
    æĸĹå¿Ĺ
    0.13
    èѦæĥķ
    0.10
    rote
    0.09
     سبÙĬÙĦ
    0.09
    /im
    0.09
    irate
    0.08
     inter
    0.08
     Walls
    0.08
    acre
    0.08
    wares
    0.08
    Activations Density 0.013%

    No Known Activations