© 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. 40008
    Prev
    Next
    INDEX
    Explanations

    little more than

    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
    åŃĿ
    -0.12
    åĨł
    -0.09
    票
    -0.09
    каÑĢ
    -0.09
    éĹ°
    -0.09
    è¾ĥ强
    -0.09
    åĹī
    -0.09
    åĬŁè¯¾
    -0.08
    çIJ¥
    -0.08
    è¾ī
    -0.08
    POSITIVE LOGITS
     mere
    0.16
    ä»ħä»ħæĺ¯
    0.13
     merely
    0.12
    åįķ纯çļĦ
    0.12
    åıªæĺ¯ä¸Ģ个
    0.12
     Ùħجرد
    0.12
    空çĻ½
    0.11
    æŀ¯çĩ¥
    0.11
     empty
    0.10
    ãģŁãģł
    0.10
    Activations Density 0.289%

    No Known Activations