© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35892
    Prev
    Next
    INDEX
    Explanations

    emotions and their consequences

    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
    åıªè¦ģæľī
    -0.10
     Ñģобой
    -0.09
    rim
    -0.09
    age
    -0.09
    AIT
    -0.08
    æ§
    -0.08
    илаÑģÑĮ
    -0.08
    åıªè¦ģ
    -0.08
    rise
    -0.08
    ymb
    -0.08
    POSITIVE LOGITS
    åįģ足
    0.11
    å·²ä¹ħçļĦ
    0.11
    满满
    0.11
    æĦ«
    0.11
    ä¹ĭæĹħ
    0.11
    å·²ä¹ħ
    0.10
    DEX
    0.10
    FUL
    0.09
    é£ŀæī¬
    0.09
    æĹºçĽĽ
    0.09
    Activations Density 0.070%

    No Known Activations