© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20607
    Prev
    Next
    INDEX
    Explanations

    repeal and abolish

    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
    管å±Ģ
    -0.09
    æħĭ
    -0.09
    говоÑĢ
    -0.08
    primitive
    -0.08
     nowhere
    -0.08
    å¼ĢéĺĶ
    -0.08
    ColumnInfo
    -0.08
    ially
    -0.08
    ãĤ£
    -0.08
    akedown
    -0.08
    POSITIVE LOGITS
    ળ
    0.10
    æİīäºĨ
    0.10
    istry
    0.09
    rug
    0.09
    ÙĬÙĬÙĨ
    0.09
    æİī
    0.09
     unused
    0.09
    åŁİå¸Ĥåıijå±ķ
    0.08
    (cancel
    0.08
    åħ°èĬ±
    0.08
    Activations Density 0.005%

    No Known Activations