© 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. 2137
    Prev
    Next
    INDEX
    Explanations

    natural and alternative medicine

    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
    APT
    -0.09
    acing
    -0.08
    åĸ·æ¶Ĥ
    -0.08
    åİĿ
    -0.08
    çĭ¡
    -0.08
    éĩįçĹĩ
    -0.08
    称èµŀ
    -0.08
    é«ĺå°Ķ
    -0.08
    èī¯æĢ§
    -0.08
    amac
    -0.08
    POSITIVE LOGITS
    天çĦ¶
    0.11
     natural
    0.10
    natural
    0.10
    èĩªçĦ¶
    0.10
    ä¼łç»Ł
    0.10
    çģ¸
    0.09
     Healing
    0.09
    Natural
    0.09
    åħ®
    0.09
     natur
    0.09
    Activations Density 0.118%

    No Known Activations