© 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. 1405
    Prev
    Next
    INDEX
    Explanations

    not only

    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
    è¯Ħæµĭ
    -0.10
    çī¹æľīçļĦ
    -0.10
    åĩŃä»Ģä¹Ī
    -0.09
    çİĭåŃIJ
    -0.09
    åĴĮåħ¶ä»ĸ
    -0.09
    çĭ¬æľīçļĦ
    -0.09
    stra
    -0.09
    sons
    -0.09
    çĬ¶åħĥ
    -0.09
    æĪ¾
    -0.09
    POSITIVE LOGITS
    å®ĥ
    0.11
     it
    0.11
     there
    0.10
     Pound
    0.09
    ively
    0.08
    è¿Ļ对äºİ
    0.08
    åĬ²
    0.08
    符åIJĪæĿ¡ä»¶
    0.08
    å®ĥæĺ¯
    0.08
     nó
    0.08
    Activations Density 0.069%

    No Known Activations