© 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. 19463
    Prev
    Next
    INDEX
    Explanations

    dietary and diet

    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
    heid
    -0.10
    ä¸įäºĨ
    -0.10
    íŀĪ
    -0.09
     dens
    -0.09
    lest
    -0.09
    åľ°å¸¦
    -0.09
    دد
    -0.09
    immers
    -0.09
    еж
    -0.09
    è¹Ī
    -0.08
    POSITIVE LOGITS
    ease
    0.10
    ëĿ½
    0.09
    åŃª
    0.09
    itian
    0.09
    ual
    0.09
    etic
    0.09
    AndServe
    0.09
    andard
    0.09
    ician
    0.09
    etics
    0.09
    Activations Density 0.023%

    No Known Activations