© 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. 62651
    Prev
    Next
    INDEX
    Explanations

    verification and validation

    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
     jaws
    -0.11
    èĮĥ
    -0.10
    ect
    -0.09
    å®Įæķ´çļĦ
    -0.09
    .AddParameter
    -0.09
    æ²¥
    -0.09
    çļĦåĽŀçŃĶ
    -0.09
    _USB
    -0.09
    .jquery
    -0.09
     lob
    -0.09
    POSITIVE LOGITS
    æł¸å®ŀ
    0.15
    éªĮè¯ģ
    0.14
     verify
    0.12
    è¯ģå®ŀ
    0.12
     Verify
    0.12
    Verify
    0.11
    verify
    0.11
     verification
    0.10
    	verify
    0.10
     validate
    0.10
    Activations Density 0.061%

    No Known Activations