© 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. 7949
    Prev
    Next
    INDEX
    Explanations

    flavor profiles and descriptions

    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
    лан
    -0.09
    éĩįè§Ĩ
    -0.09
    ichel
    -0.08
    proto
    -0.08
    ìĪĻ
    -0.08
    ç³Ļ
    -0.08
    ä¸Ģ个å¤ļ
    -0.08
    ites
    -0.08
    æĹ©æĹ©
    -0.08
    èļ¤
    -0.08
    POSITIVE LOGITS
     pop
    0.11
     Pop
    0.10
    第äºĮ大
    0.10
    æĥ³æī¾
    0.10
    åı£åij³
    0.10
    åĪ»èĭ¦
    0.10
    转åħ¥
    0.10
    pop
    0.09
    /pop
    0.09
    Pop
    0.09
    Activations Density 0.051%

    No Known Activations