© 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. 37569
    Prev
    Next
    INDEX
    Explanations

    damn near

    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
    кла
    -0.09
    cer
    -0.09
     Gear
    -0.09
    zyst
    -0.09
    etz
    -0.09
    nist
    -0.08
    榻
    -0.08
    çīĪ
    -0.08
    ارÙĬ
    -0.08
    åķ»
    -0.08
    POSITIVE LOGITS
    ement
    0.10
    ä¸Ĭ游
    0.10
     ambition
    0.09
    ä½ŀ
    0.09
    åĩŃ
    0.09
    å¾ģç¨ĭ
    0.09
    ation
    0.09
    äºĭä¸ļåıijå±ķ
    0.08
    isd
    0.08
    stellung
    0.08
    Activations Density 0.005%

    No Known Activations