© 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. 58278
    Prev
    Next
    INDEX
    Explanations

    contact information

    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
    adora
    -0.08
    rous
    -0.08
    IBM
    -0.08
    icers
    -0.08
    wake
    -0.08
    -Feb
    -0.08
    fulness
    -0.08
    prm
    -0.08
    otto
    -0.08
    âĸ¾
    -0.08
    POSITIVE LOGITS
    缺å¸Ń
    0.10
    ä¸Ľä¹¦
    0.10
    çħĬ
    0.09
    èģĶç³»æĸ¹å¼ı
    0.09
     CONTACT
    0.09
    èłĥ
    0.09
    èģĶç³»
    0.09
    山水
    0.09
    (Contact
    0.09
     Contact
    0.09
    Activations Density 0.010%

    No Known Activations