© 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. 2620
    Prev
    Next
    INDEX
    Explanations

    existence, universe, life, soul

    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
    åĭŁ
    -0.10
     ICON
    -0.09
    ereg
    -0.09
    åľ¬
    -0.09
    æ¼ķ
    -0.09
    .Act
    -0.08
    unction
    -0.08
    建æĪIJ
    -0.08
    åĮħ袱
    -0.08
     полÑĥÑĩен
    -0.08
    POSITIVE LOGITS
    ä¸ĩçī©
    0.11
    å®ĩå®Ļ
    0.10
    VEL
    0.09
    çĩİ
    0.09
    Cancellation
    0.09
    游çİ©
    0.09
    æĢ§åij½
    0.09
    iko
    0.09
    SEP
    0.09
    åĪĽéĢłäºĨ
    0.09
    Activations Density 0.182%

    No Known Activations