© 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. 19518
    Prev
    Next
    INDEX
    Explanations

    public works and municipal services

    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
    izu
    -0.10
    licable
    -0.09
    称
    -0.09
    лей
    -0.09
    å¿ĥçģµ
    -0.08
    InitStruct
    -0.08
    禾
    -0.08
    踯
    -0.08
    çīĽå¥¶
    -0.08
    orer
    -0.08
    POSITIVE LOGITS
    éļıæŶ
    0.10
    å±Ģéķ¿
    0.10
    æĢ»å±Ģ
    0.10
    çĺĹ
    0.09
     Ludwig
    0.09
    éģĵè·¯
    0.09
    梧
    0.09
    berman
    0.09
     tắc
    0.08
    azar
    0.08
    Activations Density 0.021%

    No Known Activations