© 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. 33472
    Prev
    Next
    INDEX
    Explanations

    water-related terms

    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
    lotte
    -0.11
    ulta
    -0.09
     Dispatch
    -0.09
    çĥ¤
    -0.09
    ä¸Ģå¼ł
    -0.09
    侪
    -0.09
    ardy
    -0.09
    afen
    -0.08
    åıĺéĢŁ
    -0.08
    Dispatch
    -0.08
    POSITIVE LOGITS
    falls
    0.10
    èĪŁ
    0.09
    жи
    0.09
    ä¸ĥ大
    0.09
    åķ°
    0.08
    asma
    0.08
    èѦ
    0.08
    rig
    0.08
    eso
    0.08
    pic
    0.08
    Activations Density 0.031%

    No Known Activations