© 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. 36808
    Prev
    Next
    INDEX
    Explanations

    SPDX license identifiers

    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
    åIJĽ
    -0.11
     Suzuki
    -0.08
    encies
    -0.08
    æĺ¯ä¸Ģ件
    -0.08
    uras
    -0.08
     bordered
    -0.08
     perm
    -0.08
     Carson
    -0.08
    composite
    -0.08
    éĢ
    -0.07
    POSITIVE LOGITS
    鬣
    0.12
    åĬŁè¯¾
    0.10
    èįīåİŁ
    0.09
    ç®Ń
    0.09
     кÑĢÑĥ
    0.09
    ologne
    0.09
    .Physics
    0.09
    /jav
    0.09
    åĪ»çĶ»
    0.09
    ktop
    0.09
    Activations Density 0.087%

    No Known Activations