© 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. 21551
    Prev
    Next
    INDEX
    Explanations

    beach or shore locations

    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
    ä¼ī
    -0.11
    ç©¿æ¢Ń
    -0.09
    uce
    -0.09
    山路
    -0.09
    ipro
    -0.08
    ç±³åħ°
    -0.08
     Trafford
    -0.08
    Clazz
    -0.08
    帳
    -0.08
    è£ģ
    -0.08
    POSITIVE LOGITS
    æ²Ļ滩
    0.16
    海滩
    0.16
     beaches
    0.15
     beach
    0.15
    滩
    0.13
     Beach
    0.13
    海滨
    0.12
    浪
    0.11
    shore
    0.11
    樯
    0.11
    Activations Density 0.093%

    No Known Activations