© 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. 37432
    Prev
    Next
    INDEX
    Explanations

    severely + negative impact descriptor

    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
    å¾ĢæĿ¥
    -0.09
    apl
    -0.08
    sWith
    -0.08
    aras
    -0.08
    piration
    -0.08
    rather
    -0.08
    çĥ¦æģ¼
    -0.08
    á»ijt
    -0.08
    lez
    -0.08
    atical
    -0.08
    POSITIVE LOGITS
    onal
    0.10
    æĦİ
    0.10
    ly
    0.10
    ments
    0.09
    ħ§
    0.09
    åĥ»
    0.09
    ä¸įéĶĻçļĦ
    0.09
    uess
    0.09
    est
    0.08
    LY
    0.08
    Activations Density 0.017%

    No Known Activations