© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 51892
    Prev
    Next
    INDEX
    Explanations

    day News,BSD,freÿ

    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
    nes
    -0.09
     cand
    -0.08
     liá»ĩu
    -0.08
    _agg
    -0.08
    交
    -0.08
     Mil
    -0.08
    gif
    -0.08
    å¼Ģä¸ļ
    -0.07
     Mach
    -0.07
    .comm
    -0.07
    POSITIVE LOGITS
    è¾ķ
    0.11
    åŁĤ
    0.10
    è¶ĬæĿ¥è¶Ĭ大
    0.10
    omatic
    0.09
    çľĩ
    0.09
    åħ«åį¦
    0.09
    ä¿ij
    0.09
    裱
    0.09
    çĶ¨åľ°
    0.09
     paraph
    0.09
    Activations Density 0.002%

    No Known Activations