© 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. 47786
    Prev
    Next
    INDEX
    Explanations

    preparing food and things

    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
    ocale
    -0.08
    EMS
    -0.08
    å¼ĢèįĴ
    -0.08
    æ¶ķ
    -0.08
    andal
    -0.08
    >false
    -0.08
    afia
    -0.08
     traversal
    -0.08
    ivent
    -0.08
    dock
    -0.08
    POSITIVE LOGITS
    åĩĨå¤ĩ好
    0.13
    ãģĹãģ¦ãģĬãģı
    0.13
    åĩĨå¤ĩ
    0.11
     prepared
    0.10
    åĩĨå¤ĩå·¥ä½ľ
    0.10
    çīĮ
    0.10
    éĻ·
    0.09
    .prepare
    0.09
    èĢģåĮĸ
    0.09
     prepare
    0.09
    Activations Density 0.017%

    No Known Activations