© 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. 18561
    Prev
    Next
    INDEX
    Explanations

    callback or cb

    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
    uler
    -0.10
    ä¸Ģäºĭ
    -0.08
    禳
    -0.08
    éĤ¦
    -0.08
    als
    -0.08
    ãģķãĤī
    -0.08
    uous
    -0.08
    å·´å·´
    -0.08
    æľ¬å¸Ĥ
    -0.08
    è·Ľ
    -0.08
    POSITIVE LOGITS
    ChildIndex
    0.09
    è¨Ĺ
    0.09
     Uhr
    0.09
     Spit
    0.09
    çĽİ
    0.09
    æ»ĭåij³
    0.09
    PFN
    0.08
    å¼łåħĪçĶŁ
    0.08
    atham
    0.08
     Freel
    0.08
    Activations Density 0.035%

    No Known Activations