© 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. 52010
    Prev
    Next
    INDEX
    Explanations

    form

    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
    lek
    -0.09
    .obtain
    -0.09
    ä¸Ģç¬Ķ
    -0.09
    åįłåľ°
    -0.09
    ä»Ģä¹Īåij¢
    -0.08
    ä¸Ģåı£
    -0.08
    å»ī
    -0.08
    æ±Ģ
    -0.08
    oran
    -0.08
    /mit
    -0.08
    POSITIVE LOGITS
    ateurs
    0.10
    ateur
    0.09
    æ·±è¿ľ
    0.09
    åħ»æĪIJ
    0.09
    ardi
    0.08
    /footer
    0.08
    åĪĿæŃ¥
    0.08
    ative
    0.08
    SION
    0.08
    atron
    0.08
    Activations Density 0.022%

    No Known Activations