© 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. 35123
    Prev
    Next
    INDEX
    Explanations

    water-resistant cases

    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
    çªĿ
    -0.11
    èĥĨåĽºéĨĩ
    -0.10
     translucent
    -0.10
    ç§ī
    -0.10
    åĩī
    -0.09
    åĽ½äºº
    -0.09
    åĬĪ
    -0.09
    ouro
    -0.09
    æī°
    -0.09
    ç¼ĵç¼ĵ
    -0.09
    POSITIVE LOGITS
    交ç»Ļ
    0.09
    çĭİ
    0.09
    æű
    0.09
    orio
    0.09
    éĺ²æ°´
    0.08
     Katz
    0.08
    éĺ²
    0.08
     صØŃ
    0.08
    éĺ²æĬ¤
    0.08
    çİ°éĩij
    0.08
    Activations Density 0.091%

    No Known Activations