© 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. 8476
    Prev
    Next
    INDEX
    Explanations

    stilton cheese or cheese types

    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
    ä¸ĩéĩĮ
    -0.10
    ç¾¹
    -0.09
    çĻ¾ä¸ĩ
    -0.09
    /Gate
    -0.09
    è¡®
    -0.09
    achs
    -0.09
    çĭ®åŃIJ
    -0.08
    æĻ°
    -0.08
    kees
    -0.08
    éķ¬
    -0.08
    POSITIVE LOGITS
    éĢģè´§
    0.10
    ugu
    0.10
    æľ½
    0.09
    éĻĮçĶŁ
    0.08
    èĭij
    0.08
    åĭĸ
    0.08
     Ep
    0.08
    ancement
    0.08
    带头
    0.08
    Ñģком
    0.08
    Activations Density 0.004%

    No Known Activations