© 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. 2174
    Prev
    Next
    INDEX
    Explanations

    wedding and gift

    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
    饵
    -0.10
    æĥ¨
    -0.09
    expired
    -0.08
    åĭ¾
    -0.08
    emarks
    -0.08
    æ±ģ
    -0.08
    æijĩ
    -0.08
    åİ©
    -0.08
     assured
    -0.08
    è¿ĩå¹´
    -0.08
    POSITIVE LOGITS
    亲åıĭ
    0.09
    èļĮ
    0.09
    ä¸Ģéģĵ
    0.09
    å°Ħ
    0.09
    åIJĪå½±
    0.09
    insk
    0.08
    ignKey
    0.08
    龸
    0.08
     Brush
    0.08
    brig
    0.08
    Activations Density 0.062%

    No Known Activations