© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 31280
    Prev
    Next
    INDEX
    Explanations

    over, around, from

    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
    ÑĪа
    -0.09
     fort
    -0.09
     kay
    -0.08
    pite
    -0.08
    argon
    -0.08
    anca
    -0.08
     Fort
    -0.08
    Fort
    -0.07
    为æŃ¢
    -0.07
    fort
    -0.07
    POSITIVE LOGITS
    两ä¸ī
    0.12
    åĩłåįģ
    0.12
    åįģåĩłä¸ª
    0.11
    å¤ļè¾¾
    0.11
    åĩłå¼ł
    0.11
    åĩłçĻ¾
    0.11
    åĩłåIJį
    0.11
    éĢŁåº¦å¿«
    0.10
    æķ°çĻ¾
    0.10
     amount
    0.10
    Activations Density 0.124%

    No Known Activations