© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8836
    Prev
    Next
    INDEX
    Explanations

    fermentation

    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
    iker
    -0.09
    åĨįå¤ļ
    -0.09
    azo
    -0.09
    ness
    -0.09
    auce
    -0.08
    åį°è®°
    -0.08
    aux
    -0.08
    åħļç»Ħ
    -0.08
    åIJİåı°
    -0.08
    äºĴè¡¥
    -0.08
    POSITIVE LOGITS
    .tem
    0.10
    lan
    0.10
    æ¡ħ
    0.10
    ä¾ij
    0.09
    è¿ĩåIJİ
    0.09
    æıIJéĢŁ
    0.09
    èĻº
    0.09
    èī¯å¥½
    0.09
    åĴĦ
    0.09
     /^[
    0.08
    Activations Density 0.023%

    No Known Activations