© 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. 11865
    Prev
    Next
    INDEX
    Explanations

    comparing and contrasting

    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
    åĽ°
    -0.11
    edm
    -0.10
    åħħåĪĨåıijæĮ¥
    -0.09
    ish
    -0.09
    åľ°çIJĥä¸Ĭ
    -0.09
    éģĭçĶ¨
    -0.09
    åıijæĮ¥
    -0.09
    ç¼Ľ
    -0.08
    纪å¾ĭ
    -0.08
    éģ½
    -0.08
    POSITIVE LOGITS
     compared
    0.13
     against
    0.12
    对çħ§
    0.12
     compare
    0.12
     compares
    0.11
    éķ¿çŁŃ
    0.10
    against
    0.10
     Compare
    0.10
     compareTo
    0.10
    compare
    0.09
    Activations Density 0.042%

    No Known Activations