© 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. 38031
    Prev
    Next
    INDEX
    Explanations

    temptation and resistance

    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
    è¯
    -0.10
    èĢĺ
    -0.09
    inte
    -0.08
    åIJĵ
    -0.08
    boy
    -0.08
    å½ķ
    -0.08
    çŃĽæŁ¥
    -0.08
     exp
    -0.08
     Sly
    -0.08
    zzo
    -0.08
    POSITIVE LOGITS
     temptation
    0.14
    诱æĥij
    0.13
    tempt
    0.11
     tempted
    0.10
    çıª
    0.09
     вÑĭвод
    0.09
     cầm
    0.09
    åĬ¨æīĭ
    0.09
    aller
    0.09
    åħĭåĪ¶
    0.09
    Activations Density 0.015%

    No Known Activations