© 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. 32343
    Prev
    Next
    INDEX
    Explanations

    as well as

    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
     zwar
    -0.10
    íĥĪ
    -0.09
    ä¸įä»ħè¦ģ
    -0.09
    以为
    -0.09
    以çĤº
    -0.09
    å¦ĤæѤ
    -0.09
     nevertheless
    -0.09
     either
    -0.08
    ãģ¾ãģļ
    -0.08
    è¿ĺ以为
    -0.08
    POSITIVE LOGITS
    åħ¶ä»ĸçļĦ
    0.18
    åħ¶å®ĥ
    0.14
    åħ¶ä»ĸ人
    0.13
    åħ¶ä»ĸ
    0.12
    åħ¶å®ĥéĹ®é¢ĺ
    0.12
     others
    0.11
    åĪ«çļĦ
    0.11
    åħ¶ä»ĸåĽ½å®¶
    0.10
    æĪij个人
    0.10
     ones
    0.10
    Activations Density 0.108%

    No Known Activations