© 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. 37435
    Prev
    Next
    INDEX
    Explanations

    drought

    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
    Ľ
    -0.12
    ssf
    -0.10
    å¾Ĺ太
    -0.09
    赫
    -0.09
    京津
    -0.09
    lder
    -0.09
    erner
    -0.08
    åľ¨ä¸Ģèµ·
    -0.08
    ounds
    -0.08
    ryo
    -0.08
    POSITIVE LOGITS
    inx
    0.09
    aspers
    0.09
    çĬĬ
    0.08
    enthal
    0.08
    snap
    0.08
    sd
    0.08
    èĭ
    0.08
    ong
    0.08
    riendly
    0.08
    à¸ĩ
    0.08
    Activations Density 0.006%

    No Known Activations