© 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. 52086
    Prev
    Next
    INDEX
    Explanations

    must say

    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
    æģ°
    -0.08
    ç¨Ĺ
    -0.08
    è¿İ
    -0.08
    çı²
    -0.08
     ÙħØŃÙĦ
    -0.08
     unge
    -0.08
    ainer
    -0.08
    åŁ¤
    -0.08
    磴
    -0.08
    çĬ¶åħĥ
    -0.08
    POSITIVE LOGITS
    说æĺ¯
    0.21
    说
    0.21
    åľ°è¯´
    0.20
    說
    0.18
     say
    0.17
    è¿Ļä¹Ī说
    0.17
    说æĪij
    0.16
     ÑģказаÑĤÑĮ
    0.16
     saying
    0.16
    æĿ¥è¯´
    0.16
    Activations Density 0.062%

    No Known Activations