© 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. 54565
    Prev
    Next
    INDEX
    Explanations

    climate and policy measures

    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
    åħ¼åħ·
    -0.09
    è·ijäºĨ
    -0.09
    çĶ¨äººåįķä½į
    -0.09
    itan
    -0.09
    zed
    -0.09
     khÄĥn
    -0.09
    è¯Ħ为
    -0.09
    åĬ³åĬ¡
    -0.09
    涿
    -0.09
    æĮĪ
    -0.09
    POSITIVE LOGITS
    åīĬåĩı
    0.12
    æĿ¡çº¦
    0.11
    éĵ²
    0.10
    صار
    0.10
    åĩıå°ij
    0.09
    çķ¹
    0.09
    éĻįå¹ħ
    0.09
    FileType
    0.09
     reductions
    0.09
    大æī¹
    0.09
    Activations Density 0.058%

    No Known Activations