© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37891
    Prev
    Next
    INDEX
    Explanations

    blah blah

    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
    Ħ件
    -0.10
    bcc
    -0.09
    aal
    -0.09
     Strand
    -0.09
     Stout
    -0.09
    åĮĸè¿Ľç¨ĭ
    -0.08
     bú
    -0.08
    OOT
    -0.08
     lòng
    -0.08
    adal
    -0.08
    POSITIVE LOGITS
    ä¸Ģ大åłĨ
    0.13
    estar
    0.11
    енÑĮк
    0.10
    åľ°çIJĥä¸Ĭ
    0.09
    ä¸ĢåłĨ
    0.09
    ä¸įåłª
    0.09
    ä½ŀ
    0.09
    çĥĤ
    0.08
    ork
    0.08
    æµģæĦŁ
    0.08
    Activations Density 0.021%

    No Known Activations