© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 20948
    Prev
    Next
    INDEX
    Explanations

    mining, reclamation, scourge, Virginia

    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
    çĮ¾
    -0.10
    éļIJ
    -0.10
    è¹Ļ
    -0.10
    æĶĢ
    -0.10
    æ°´åºĵ
    -0.09
     underage
    -0.09
    æĮĤåľ¨
    -0.09
    éļ±
    -0.09
    asca
    -0.09
    峪
    -0.09
    POSITIVE LOGITS
    á»įn
    0.09
    çķ¸
    0.09
    ãģĦãģ§
    0.08
    åĭĭ
    0.08
    å³Ĵ
    0.08
    åłĨ
    0.08
    æµģæ°´
    0.08
    pra
    0.08
    èĤĭ
    0.08
    gom
    0.08
    Activations Density 0.010%

    No Known Activations