© 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. 21540
    Prev
    Next
    INDEX
    Explanations

    opinions on or about

    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
    orra
    -0.09
    åĸŁ
    -0.09
    bson
    -0.09
    éļ¶å±ŀ
    -0.09
    追éļı
    -0.09
    aghan
    -0.08
    çĶµåĬ¨
    -0.08
    æĢ¨
    -0.08
    ,content
    -0.08
     trùng
    -0.08
    POSITIVE LOGITS
     regarding
    0.09
    伪
    0.08
     about
    0.08
    é£İæ°´
    0.08
    çķ´
    0.08
    åħ³äºİ
    0.08
    éĥ¨ä¸»ä»»
    0.08
    _EXP
    0.08
    管çIJĨä¸Ńå¿ĥ
    0.08
    ingles
    0.08
    Activations Density 0.044%

    No Known Activations