© 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. 19497
    Prev
    Next
    INDEX
    Explanations

    amino acid

    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
    èĥĥåı£
    -0.09
    ede
    -0.09
    rimp
    -0.09
    OrUpdate
    -0.09
    odium
    -0.08
    ç±½
    -0.08
    çİ¢
    -0.08
    aney
    -0.08
    mtx
    -0.08
    enuity
    -0.08
    POSITIVE LOGITS
    楣
    0.10
    èĤĦ
    0.09
    å¥ķ
    0.09
    ä¹IJæĦı
    0.09
    ç¼°
    0.09
    ä¿¡èµĸ
    0.09
    çĤ¹å¤ļ
    0.09
    aza
    0.09
    PHY
    0.09
    åĩłæŃ¥
    0.09
    Activations Density 0.138%

    No Known Activations