© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53285
    Prev
    Next
    INDEX
    Explanations

    eating healthy or unhealthy habits

    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
     intim
    -0.09
    /from
    -0.09
    -eslint
    -0.09
    æ°¸åĪ©
    -0.09
    eda
    -0.09
    -ever
    -0.09
    亲çĪ±
    -0.09
    mente
    -0.09
    bred
    -0.08
    ombo
    -0.08
    POSITIVE LOGITS
    çĨ
    0.09
    /dr
    0.09
    æĻļé¥Ń
    0.09
    ting
    0.09
    äºĽä»Ģä¹Ī
    0.09
    ters
    0.09
     habits
    0.09
    飽
    0.09
    飯
    0.09
    tings
    0.09
    Activations Density 0.015%

    No Known Activations