© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50852
    Prev
    Next
    INDEX
    Explanations

    company and its subsidiaries

    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
    åĨ²
    -0.09
    ps
    -0.09
    instein
    -0.09
    entic
    -0.08
    æ¶Ľ
    -0.08
    chi
    -0.08
    _confirmation
    -0.08
    onium
    -0.08
    osphere
    -0.08
    éĤķ
    -0.08
    POSITIVE LOGITS
    ancellable
    0.10
    emente
    0.10
    æīĢæľī人éĥ½
    0.09
    åŀĮ
    0.09
    å¸ĪåħĦ
    0.09
    客人
    0.09
    å¼Ģåĩº
    0.09
    许å¤ļ人
    0.09
    åĽŀäºĭ
    0.09
    elage
    0.09
    Activations Density 0.037%

    No Known Activations