© 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. 35622
    Prev
    Next
    INDEX
    Explanations

    jealousy and envy

    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
    iversal
    -0.09
    жÑĥ
    -0.09
    fall
    -0.09
    duct
    -0.08
    expl
    -0.08
     smack
    -0.08
    å±ŀäºİèĩªå·±
    -0.08
    QS
    -0.08
    æ´¹
    -0.08
    el
    -0.08
    POSITIVE LOGITS
    海峡
    0.10
    .Marshal
    0.10
    vine
    0.10
    çĸĻ
    0.10
    èĤļ
    0.09
    å·´æĭī
    0.09
    ape
    0.09
    第ä¸Ģä½į
    0.09
     Jal
    0.09
    ç»Ĩå¿ĥ
    0.09
    Activations Density 0.003%

    No Known Activations