© 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. 32726
    Prev
    Next
    INDEX
    Explanations

    worth the value

    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
    åĢŁæѤ
    -0.09
    æĪŁ
    -0.09
    ãģ£ãģ
    -0.09
    REFER
    -0.08
    èĭ
    -0.08
    ãĤĪãģĭãģ£ãģŁ
    -0.08
    çĦī
    -0.08
    Pes
    -0.08
     Loss
    -0.08
    (prev
    -0.07
    POSITIVE LOGITS
    以èĩ³äºİ
    0.09
    åĶ¾
    0.09
    让èĩªå·±
    0.09
    å°±è¿Ļä¹Ī
    0.09
    AMI
    0.09
    immel
    0.09
    ä¼ĹæīĢ
    0.09
    çĭĤ
    0.09
    ä¼Ĺ
    0.09
    wright
    0.08
    Activations Density 0.016%

    No Known Activations