© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 31619
    Prev
    Next
    INDEX
    Explanations

    URI, URL, guid, persistent 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
    æĪij们éĥ½
    -0.10
    龸çİĭ
    -0.09
    å¸ĪèĮĥ
    -0.09
    æµģ泪
    -0.08
     Tape
    -0.08
    å¼ĩ
    -0.08
    enga
    -0.08
    é¥®é£Ł
    -0.08
    té
    -0.08
    çĸ
    -0.08
    POSITIVE LOGITS
    DataURL
    0.09
     url
    0.09
    .url
    0.09
    éĶļ
    0.09
    æ³¾
    0.09
    寻
    0.09
    å®ļçĤ¹
    0.09
    åĿĢ
    0.09
     URL
    0.09
    毫ä¸į
    0.09
    Activations Density 0.159%

    No Known Activations