© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 61919
    Prev
    Next
    INDEX
    Explanations

    drought and its effects

    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
    jing
    -0.11
    ritten
    -0.10
    Ñģан
    -0.10
    éŨåīį
    -0.09
    urch
    -0.09
    irate
    -0.09
    åľ¨æł¡
    -0.09
     Pert
    -0.09
    åijĬè¯ī她
    -0.09
    sex
    -0.08
    POSITIVE LOGITS
     drought
    0.16
    å¹²æĹ±
    0.14
    æĹ±
    0.11
    渴
    0.10
     parch
    0.10
    æİĤ
    0.10
    çī©ä»·
    0.09
    缺
    0.09
    spell
    0.09
    å¹²çĩ¥
    0.09
    Activations Density 0.046%

    No Known Activations