© 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. 7967
    Prev
    Next
    INDEX
    Explanations

    clearly comfortable

    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
    æŃ£å¥½
    -0.13
    çĦī
    -0.11
    æijŃ
    -0.10
    æī£
    -0.09
    å·®çĤ¹
    -0.09
    æģ°æģ°
    -0.09
    åĪļ好
    -0.09
    éĢĨ转
    -0.09
     пÑĢава
    -0.08
    abil
    -0.08
    POSITIVE LOGITS
    æĻ°
    0.11
    çıŃ
    0.09
    åĨĻçĿĢ
    0.09
    èªĬ
    0.09
    åĶĩ
    0.08
    èĥ½çľĭåĩº
    0.08
     rÃłng
    0.08
    anje
    0.08
    _wind
    0.08
    çķĮéĻIJ
    0.08
    Activations Density 0.063%

    No Known Activations