© 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. 10323
    Prev
    Next
    INDEX
    Explanations

    agreement and acknowledgment

    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
    æ¶Ī
    -0.10
    æ¿ł
    -0.09
     kob
    -0.09
    åĪĽä¸ļèĢħ
    -0.08
    æģ°å¥½
    -0.08
    auce
    -0.08
     Wade
    -0.08
    豪
    -0.08
    èŃ¦ç¤º
    -0.08
    ECTOR
    -0.08
    POSITIVE LOGITS
    åħ±è¯Ĩ
    0.14
     agreed
    0.13
    毫æĹłçĸij
    0.11
     agrees
    0.11
     agreement
    0.11
    åħ¥åĽ´
    0.11
     agree
    0.11
     uncont
    0.11
    åħ¬è®¤
    0.11
    æĹłçĸij
    0.10
    Activations Density 0.070%

    No Known Activations