© 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. 6972
    Prev
    Next
    INDEX
    Explanations

    order matters

    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
    çķ¦
    -0.09
    çĶŁçĶŁ
    -0.09
    åĸŁ
    -0.09
    åħħåĪĨåĪ©çĶ¨
    -0.09
    è¾ı
    -0.09
    éªĬ
    -0.09
    èIJĺ
    -0.09
    è¢ĸ
    -0.09
    æIJ¬å®¶
    -0.09
    \Configuration
    -0.08
    POSITIVE LOGITS
    顺åºı
    0.15
    åħĪåIJİ
    0.12
    äºĭæĥħ
    0.11
     sequence
    0.10
    sequence
    0.10
     seq
    0.09
    .seq
    0.09
    .sequence
    0.09
    åħĪ
    0.09
    åºı
    0.09
    Activations Density 0.077%

    No Known Activations