© 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. 55915
    Prev
    Next
    INDEX
    Explanations

    floodwaters and flooding

    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
    绺
    -0.09
    è·Łè¸ª
    -0.09
    åĮ¿
    -0.09
    çijľ
    -0.09
    迹
    -0.09
    å¿łå®ŀ
    -0.09
    èĢ½
    -0.08
    -track
    -0.08
    ç»Ĭ
    -0.08
    åıijå±ķ壮大
    -0.08
    POSITIVE LOGITS
    洪水
    0.12
     flood
    0.12
    æķijçģ¾
    0.10
     FEMA
    0.10
    éĺ²æ±Ľ
    0.10
    éĺ²
    0.10
    åįĵè¶Ĭ
    0.09
     Flood
    0.09
    éĺ²çº¿
    0.09
     floods
    0.09
    Activations Density 0.055%

    No Known Activations