© 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. 33818
    Prev
    Next
    INDEX
    Explanations

    at least in part

    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
    çĶļèĩ³è¿ĺ
    -0.10
    çĶļèĩ³
    -0.09
    æĹ¢æĺ¯
    -0.09
    åĪ°åºķ
    -0.09
     даже
    -0.09
    åħ¨åĽ½åIJĦåľ°
    -0.08
    ä¸ĢåĪĩ
    -0.08
    å½ĵçĦ¶
    -0.08
    PAD
    -0.08
    ernal
    -0.08
    POSITIVE LOGITS
    èµ·åĪ°äºĨ
    0.09
    åijĬ
    0.09
     ones
    0.09
    èµ·åĪ°
    0.09
    éĤ£æł·
    0.08
     Carp
    0.08
    建æĪIJ
    0.08
    çŁŃæľŁåĨħ
    0.08
    æ¯Ķè¾ĥ好
    0.08
    _FIN
    0.08
    Activations Density 0.016%

    No Known Activations