© 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. 22360
    Prev
    Next
    INDEX
    Explanations

    workers' paradise, increasing control, working-class family, enemies of revolution

    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
    éªŀ
    -0.09
    çĶŁæĹ¥
    -0.09
    è¿Ļå¥Ĺ
    -0.08
    å¦ĤæľŁ
    -0.08
    è´©åįĸ
    -0.08
    åĬ³åĬ¡
    -0.08
    循çݯ
    -0.08
     Inflate
    -0.08
    éĥ¦
    -0.08
    æĬķ注
    -0.08
    POSITIVE LOGITS
    ìĪĻ
    0.10
    ä¸ĵåĮº
    0.10
    å¨ĺ
    0.09
    ç»Ħç»ĩå®ŀæĸ½
    0.09
    ijn
    0.09
    éĺ¶çº§
    0.08
    ervas
    0.08
    nants
    0.08
     hardened
    0.08
    移æ°ij
    0.08
    Activations Density 0.025%

    No Known Activations