© 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. 31115
    Prev
    Next
    INDEX
    Explanations

    step family members or laws

    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
    åİĮ
    -0.09
     пÑĢим
    -0.09
     Jays
    -0.09
    æ£Ģ
    -0.09
    æĺİçıł
    -0.09
    çĤħ
    -0.09
    æIJĢ
    -0.09
    个å°ı
    -0.08
    éĶĢ
    -0.08
    ä¿ħ
    -0.08
    POSITIVE LOGITS
    æĪIJçĨŁ
    0.11
    ä¸Ī
    0.10
    å±Ĥåĩºä¸įç©·
    0.10
     Came
    0.09
    æĪ¿ä¸ľ
    0.09
    èĤĺ
    0.09
    碰åĪ°
    0.09
    coe
    0.09
    alls
    0.09
    tur
    0.09
    Activations Density 0.078%

    No Known Activations