© 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. 9479
    Prev
    Next
    INDEX
    Explanations

    protein electrophoresis

    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
    .acc
    -0.10
    axed
    -0.09
    iox
    -0.09
    æ§Į
    -0.09
     pil
    -0.08
    ترا
    -0.08
    éĴļ
    -0.08
     pill
    -0.08
    åŁİå¸Ĥ管çIJĨ
    -0.08
    å²Ń
    -0.08
    POSITIVE LOGITS
    Earn
    0.10
    ENTER
    0.10
    çIJ
    0.09
    紧迫
    0.08
    ниÑĨÑĭ
    0.08
     ENTER
    0.08
    æľīæľŁ
    0.08
    _Action
    0.08
    isol
    0.08
    ester
    0.08
    Activations Density 0.357%

    No Known Activations