© 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. 3467
    Prev
    Next
    INDEX
    Explanations

    stay updated or ahead

    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
    éľĦ
    -0.09
    家éŨåı£
    -0.09
    ä¸įå¾Ĺ转载
    -0.09
    aison
    -0.08
    èµĦæºIJåħ±äº«
    -0.08
    åĩ¼
    -0.08
    unable
    -0.08
    桧
    -0.08
     Sharing
    -0.08
    åħ±äº«
    -0.08
    POSITIVE LOGITS
    åIJģ
    0.10
    éĻħ
    0.10
    ÄĦ
    0.09
    çīŁ
    0.09
    iju
    0.09
    arih
    0.09
     Blanch
    0.09
    ValueCollection
    0.09
    ahead
    0.09
    å¾Ģè¿Ķ
    0.09
    Activations Density 0.023%

    No Known Activations