© 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. 5261
    Prev
    Next
    INDEX
    Explanations

    irregularity and regularity

    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
    enic
    -0.10
    åıĪä¸Ģ次
    -0.10
    AGER
    -0.09
     miejsc
    -0.09
    ÑĮÑı
    -0.09
    建åįİ
    -0.08
    踽
    -0.08
    æİĢèµ·
    -0.08
    åıĻäºĭ
    -0.08
    à¸Ķ
    -0.08
    POSITIVE LOGITS
    ities
    0.11
    Regular
    0.10
     Regular
    0.10
    regular
    0.09
    ä½ľæģ¯
    0.09
    çķħ
    0.08
     irregular
    0.08
     regular
    0.08
    çĵ£
    0.08
    çķħéĶĢ
    0.08
    Activations Density 0.051%

    No Known Activations